Methods and electronic devices for identifying forged images

Abstract

This application provides a method and electronic device for identifying forged images. The method includes: when a first image is displayed on the screen of the electronic device, performing forgery analysis on the first image; when it is identified that one or more objects in the first image contain forged objects and / or the scene of the first image is a forged scene and / or one or more elements associated with the first image contain forged elements, the electronic device issues a first alert to the user. The first alert is used to mark the forged objects and / or forged scenes and / or forged elements present in the first image. Through this method and electronic device, forgery analysis can be performed on both local parts of images or videos and on the overall scene of images or videos, thereby effectively identifying forged images and providing timely, more granular alerts to users, improving the security of users' internet use.

Description

Technical Field

[0001] This application relates to the field of identifying forged images, and more specifically, to a method and electronic device for identifying forged images. Background Technology

[0002] With the rapid development of large-scale artificial intelligence (AI) models, images forged using AI models can be so realistic that they are indistinguishable from the real thing. While this brings people an advanced technological experience, it has also led to a large number of cases of online fraud using forged images, causing great distress to people.

[0003] Therefore, there is an urgent need to provide a method that can effectively identify forged images in order to improve the security of users' Internet use. Summary of the Invention

[0004] This application provides a method and electronic device for identifying forged images. The method and electronic device can perform forgery analysis on both local parts of images or videos (e.g., forged human figures) and the overall scene of images or videos. This can effectively identify forged images and provide users with more granular reminders in a timely manner, thereby improving the security of users' Internet use and providing better reference for users to make subsequent decisions.

[0005] In a first aspect, a method for identifying forged images is provided, the method comprising: when a first image is displayed on a screen of an electronic device, the electronic device performs forgery analysis on the first image; when it is identified that one or more objects in the first image contain forged objects and / or the scene of the first image is a forged scene and / or one or more elements associated with the first image contain forged elements, the electronic device issues a first alert to a user, the first alert being used to mark the forged objects and / or forged scenes and / or forged elements present in the first image.

[0006] In this embodiment, it is possible to perform forgery analysis on both local objects in an image or video and the overall scene of the image or video. This enables the effective identification of forged images and timely, more granular alerts to users, thereby improving the security of users' internet use and providing better references for users to make subsequent decisions.

[0007] In conjunction with the first aspect, in one possible implementation, when the first image is displayed on the screen of an electronic device, the electronic device performs forgery analysis on the first image, including: when the first image is displayed on the screen of the electronic device, the electronic device issues a second reminder to the user, the second reminder being used to remind the user whether the first image has been forged; and based on the user's confirmation that the first image has been forged, the electronic device performs forgery analysis on the first image.

[0008] In this embodiment, when an electronic device detects a displayed image, it can ask the user whether to perform forgery analysis on the image. This provides the user with a convenient entry point to trigger forgery analysis, and the user can also choose whether to perform forgery analysis on the current image, thus improving the user experience of using the electronic device.

[0009] In conjunction with the first aspect, in one possible implementation, when a first image is displayed on the display screen of an electronic device, performing forgery analysis on the first image includes: when the first image is displayed on the display screen of the electronic device, the electronic device performs forgery analysis on the first image based on a first operation performed by a user on the first image.

[0010] In this embodiment, the electronic device does not automatically trigger the forgery analysis of the image. Instead, the electronic device will perform the forgery analysis of the image based on the user's active triggering operation, which can give the user more freedom of operation.

[0011] In conjunction with the first aspect, in one possible implementation, the first operation includes: the user dragging the first image to the interactive area of ​​the electronic device, or the user selecting the first image on the display screen of the electronic device, or the user performing a touch operation on a first control, the first control being displayed on the same interface as the first image, the first control being used to trigger the electronic device to recognize the first image; the user inputting a first instruction to the electronic device, the first instruction being used to instruct the first image to be forged.

[0012] The user inputs a first command into the electronic device. This can be done by the user inputting the first command via voice, text input, or other means. This application does not limit the scope of the first command input.

[0013] In this embodiment, the user can first trigger the recognition of the image to be recognized by dragging, selecting or clicking the relevant controls, and then issue a command for the first image to actively trigger the forgery analysis of the image to be recognized. This not only provides the user with an entry point to actively trigger image forgery analysis, but also enhances the user's enjoyment of using electronic devices.

[0014] In conjunction with the first aspect, in one possible implementation, the first operation includes: a user dragging the first image to the voice interaction area of ​​the electronic device; the user issuing a first voice command to the electronic device, the first voice command being used to instruct the first image to be forged.

[0015] In this embodiment, users can actively trigger forgery analysis of the image to be identified by combining dragging and dropping operations with voice commands. This provides users with an entry point to actively trigger image forgery analysis and enhances the fun of using electronic devices.

[0016] In conjunction with the first aspect, in one possible implementation, the first operation includes: a user circling the first image on the display screen of the electronic device; the user issuing a first voice command to the electronic device, the first voice command being used to instruct the first image to undergo forgery analysis.

[0017] In this embodiment, users can actively trigger forgery analysis of the image to be identified by combining the selection operation of the image to be identified with voice commands. This not only provides users with an entry point to actively trigger image forgery analysis, but also enhances the fun of using electronic devices.

[0018] In conjunction with the first aspect, in one possible implementation, the first operation includes: a user performing a touch operation on the first control; the user issuing a first voice command to the electronic device, the first voice command being used to instruct the electronic device to perform forgery analysis on the first image based on the recognition result.

[0019] In this embodiment, users can use specific controls in conjunction with voice commands to actively trigger forgery analysis of the image to be identified. This provides users with an entry point to actively trigger image forgery analysis and enhances the user's enjoyment of using electronic devices.

[0020] In conjunction with the first aspect, in one possible implementation, when the first image is detected to be displayed on the display screen of the electronic device, the electronic device displays a second control on the display screen, the first operation including: the user clicking the first live window or clicking the first card.

[0021] The second control could be, for example, the first live window or the first card.

[0022] In this embodiment, a live view window or other controls can be used as the entry point to trigger the forgery detection of the image. Furthermore, the live view window occupies a small screen area and will not affect the user's browsing and operation of the displayed content.

[0023] In conjunction with the first aspect, in one possible implementation, during the process of the electronic device performing forgery analysis on the first image, a second live view window is displayed on the screen of the electronic device to remind the user that the electronic device is performing forgery analysis on the first image; and / or when it is identified that there is a forged object in one or more objects in the first image and / or the scene of the first image is a forged scene, and / or there is a forged element in one or more elements output associated with the first image, a third live view window is displayed on the screen of the electronic device to display the first reminder.

[0024] In this embodiment, the live view window can also remind the user that the image is being analyzed for forgery, and can also display the forgery analysis results to the user as an entry point to trigger the forgery identification of the image. Furthermore, since the live view window occupies a small screen area, it will not affect the user's browsing and operation of the displayed content.

[0025] In conjunction with the first aspect, in one possible implementation, the electronic device performs forgery analysis on the first image, including: the electronic device performs forgery analysis on the first image based on the associated information corresponding to the first image, wherein the associated information of the first image includes sound information and / or geographical location information associated with the first image.

[0026] Through the embodiments of this application, for example, it is possible to identify sounds that do not match the user's lip movements in the image, and to identify synthesized sounds, thereby enabling more accurate identification of forged images.

[0027] In conjunction with the first aspect, in one possible implementation, the method further includes: when the electronic device issues the first reminder to the user, it provides the user with an interception entry and / or a reporting entry, wherein the interception entry is used to trigger an interception mechanism for the first image, and the reporting entry is used to trigger a report that the first image is a fake image.

[0028] In this embodiment of the application, when an image is detected to be a forged image, the electronic device can simultaneously provide the user with an interception entry and / or a reporting entry for forged images, providing the user with an entry for subsequent processing of forged images.

[0029] In conjunction with the first aspect, in one possible implementation, forgery analysis of the first image includes: performing forgery analysis on the first image using a first model.

[0030] In conjunction with the first aspect, in one possible implementation, the first model is trained based on multiple images and multiple forgery analysis results corresponding one-to-one with the multiple images. The input of the first model is an image, and the output is the forgery analysis result of the image, wherein at least one of the multiple images is a forgery scene.

[0031] In conjunction with the first aspect, in one possible implementation, the first image includes pictures and / or videos.

[0032] In conjunction with the first aspect, in one possible implementation, the first image includes one or more of the following images: a video call displayed by the electronic device while running a video call application; a live video displayed by the electronic device while running a live video application; a video and / or image displayed by the electronic device while running a social application; a video and / or image displayed by the electronic device while running a browser application; a video and / or image displayed by the electronic device while running a news application; and a video and / or image displayed by the electronic device while running a gallery application.

[0033] The method provided in this application can be applied to scenarios such as video calls, live video streaming, web browsing, chat, news browsing, and gallery browsing.

[0034] In conjunction with the first aspect, in one possible implementation, one or more objects in the first image include one or more of people, animals, and objects.

[0035] In this embodiment, forgery analysis can be performed on people, animals, and objects in images, which can more effectively identify forged images and promptly alert users, thereby improving the security of users' Internet use.

[0036] In a second aspect, an electronic device is provided, comprising one or more processors and one or more memories, and one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, and the one or more computer programs include instructions that, when executed by the one or more processors, cause the electronic device to perform the methods of the first aspect or any possible implementation thereof.

[0037] Thirdly, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed, implement the method of the first aspect or any possible implementation thereof.

[0038] Fourthly, a chip is provided, wherein instructions are stored that, when executed on a device, cause the chip to perform the methods described in the first aspect or any possible implementation thereof.

[0039] Fifthly, a computer program product is provided, which stores a computer program or instructions that, when executed, implement the method in the first aspect or any possible implementation of the first aspect. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0041] Figure 2 This is a schematic diagram illustrating the operation of enabling the function of an electronic device to identify forged images, as provided in an embodiment of this application.

[0042] Figure 3 This is another operational diagram illustrating how to enable the function of an electronic device to identify forged images, provided in an embodiment of this application.

[0043] Figure 4 These are schematic diagrams of interfaces that provide users with information about the forgery analysis results of images, as provided in the embodiments of this application.

[0044] Figure 5 This is a schematic diagram illustrating an operation for triggering forgery analysis of an image, provided in an embodiment of this application.

[0045] Figure 6 This illustration shows another operation diagram for triggering forgery analysis of an image, provided by an embodiment of this application.

[0046] Figure 7 This illustration shows another operation diagram for triggering forgery analysis of an image, provided by an embodiment of this application.

[0047] Figure 8 This is another schematic diagram of an operation that triggers forgery analysis of an image, provided in an embodiment of this application;

[0048] Figure 9 This is another schematic diagram of an operation that triggers forgery analysis of an image, provided in an embodiment of this application;

[0049] Figure 10 This is another schematic diagram of an operation that triggers forgery analysis of an image, provided in an embodiment of this application;

[0050] Figure 11 This is another schematic diagram of an operation that triggers forgery analysis of an image, provided in an embodiment of this application;

[0051] Figure 12 This illustration shows a schematic diagram of an interface for displaying forgery analysis results provided in an embodiment of this application;

[0052] Figure 13This is a schematic flowchart illustrating a method for identifying forged images provided in an embodiment of this application;

[0053] Figure 14 This is a schematic flowchart illustrating another method for identifying forged images provided in an embodiment of this application;

[0054] Figure 15 This is a schematic flowchart illustrating another method for identifying forged images provided in an embodiment of this application;

[0055] Figure 16 This is a schematic flowchart of a method for training a first model for image forgery analysis, provided in an embodiment of this application.

[0056] Figure 17 This is a system architecture diagram for video forgery analysis provided in an embodiment of this application;

[0057] Figure 18 This is a system architecture diagram for image forgery analysis provided in an embodiment of this application. Detailed Implementation

[0058] The technical solutions of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments.

[0059] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; "and / or" in this text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "plural" or "multiple" refers to two or more than two.

[0060] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0061] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one, two, or more than two. The term “and / or” is used to describe the relationship between related objects, indicating that three relationships may exist; for example, A and / or B can indicate: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character “ / ” generally indicates that the preceding and following related objects are in an “or” relationship.

[0062] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "one embodiment," "some embodiments," "another embodiment," "other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0063] The methods provided in this application can be applied to electronic devices such as mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). This application does not impose any restrictions on the specific type of electronic device.

[0064] For example, Figure 1A schematic diagram of the structure of electronic device 100 is shown. Electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a USB interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0065] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0066] Processor 110 may include one or more processing units, such as application processors (APs), modem processors, GPUs, ISPs, controllers, memory, video codecs, DSPs, baseband processors, and / or NPUs. These different processing units may be independent devices or integrated into one or more processors.

[0067] The controller can be the nerve center and command center of the electronic device 100. The controller can generate operation control signals according to the instruction opcode and timing signals to complete the control of fetching and executing instructions.

[0068] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0069] USB interface 130 is a USB standard compliant interface, specifically a Mini USB interface, Micro USB interface, USB Type-C interface, etc. USB interface 130 can be used to connect a charger to charge electronic device 100, and can also be used for data transfer between electronic device 100 and peripheral devices. This interface can also be used to connect other electronic devices, such as AR devices.

[0070] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0071] The charging management module 140 receives charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 receives charging input from the wired charger via the USB interface 130. In some wireless charging embodiments, the charging management module 140 receives wireless charging input via the wireless charging coil of the electronic device 100. While charging the battery 142, the charging management module 140 can also supply power to the electronic device via the power management module 141.

[0072] The power management module 141 connects the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, providing power to the processor 110, internal memory 121, external memory, display screen 194, camera 193, and wireless communication module 160, etc. The power management module 141 can also monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance). In some other embodiments, the power management module 141 may also be located within the processor 110. In other embodiments, the power management module 141 and the charging management module 140 may be located in the same device.

[0073] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0074] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0075] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a miniature LED, a microLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, electronic device 100 may include one or N displays 194, where N is a positive integer greater than 1.

[0076] The external storage interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external storage interface 120 to perform data storage functions. For example, music, video, and other files can be saved on the external memory card.

[0077] Internal memory 121 can be used to store computer executable program code, which includes instructions. Processor 110 executes various functional applications and data processing of electronic device 100 by running the instructions stored in internal memory 121. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of electronic device 100 (such as audio data, phonebook, etc.). Furthermore, internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0078] Buttons 190 include a power button, volume buttons, etc. Buttons 190 can be mechanical buttons or touch-sensitive buttons. Electronic device 100 can receive button input and generate key signal inputs related to user settings and function control of electronic device 100.

[0079] Motor 191 can generate vibration alerts. Motor 191 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can correspond to touch operations performed on different applications (such as taking photos, playing audio, etc.). Motor 191 can also correspond to different vibration feedback effects for touch operations performed on different areas of the display screen 194. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0080] Indicator 192 can be an indicator light, used to indicate charging status, power changes, or to indicate messages, missed calls, notifications, etc.

[0081] The SIM card interface 195 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 195 to make contact with or separate from the electronic device 100.

[0082] It should be understood that the phone cards in the embodiments of this application include, but are not limited to, SIM cards, eSIM cards, universal subscriber identity modules (USIM), universal integrated circuit cards (UICC), etc.

[0083] In some embodiments, the electronic device 100 may be, for example, a central control screen, a television, a desktop computer, a laptop computer, a vehicle screen, or a portable electronic device such as a mobile phone, a foldable screen, a tablet computer, a watch, a bracelet, or a smart home device such as a smart speaker or a smart screen.

[0084] It should be understood that the technical solutions in the embodiments of this application can be used in systems such as Android, iOS, and HarmonyOS.

[0085] The technical solutions of this application embodiment can be applied, for example, to electronic devices with display functions. Exemplarily, they can be applied to televisions, desktop computers, laptops, in-vehicle screens, central control screens, and portable electronic devices such as mobile phones, foldable screens, tablets, watches, and wristbands. They can also be applied to smart home devices, such as smart speakers and smart screens, and to electronic devices in future networks or in future evolved public land mobile networks (PLMNs). This technical solution can, for example, be specifically used to identify scenarios involving forged images or videos.

[0086] With the rapid development of large-scale artificial intelligence (AI) models, images created using these models can be so realistic that they are almost indistinguishable from the real thing. While this brings people an advanced technological experience, it has also led to numerous cases of online fraud using forged images. For example, during video calls, AI models can be used to swap faces, impersonating acquaintances to defraud victims of their money. Another example is the use of AI models to fabricate the behavior and environment of a person, using this as a basis to spread rumors, causing significant distress to people.

[0087] In some embodiments, face-swapping detection can be performed on images to detect whether the people in the images have undergone face-swapping processing, thereby identifying forged images that have undergone face-swapping processing.

[0088] While this method can identify forged images that have undergone face swapping, the identification is limited to the people in the image. It can only identify whether the people in the image have had their faces swapped, but it cannot identify forged scenes in the image or video. This makes it ineffective in dealing with a variety of fraudulent methods that are difficult to prevent. Fraudulent activities using forged images will still cause great distress to people.

[0089] In view of this, embodiments of this application provide a method and electronic device for identifying forged images. Through this method and electronic device, partial synthetic objects (e.g., synthetic human figures, synthetic animals, synthetic items) and / or overall synthetic scenes in images or videos can be identified, thereby effectively identifying forged images and promptly alerting users to improve the security of users' Internet use.

[0090] For example, taking a mobile phone as an electronic device, Figure 2 This illustration shows an operational diagram of enabling the function of an electronic device to identify forged images, according to an embodiment of this application. Figure 2 As shown, the function of recognizing forged images of electronic device 200 can be enabled through the system settings of electronic device 200.

[0091] In one example, through the system settings of electronic device 200, the display interface of electronic device 200 can be made to display as follows: Figure 2 The interface shown includes a control 201, which is used to enable the electronic device 200's function of identifying counterfeit images. The interface may also include explanatory text about the function of control 201, such as "When enabled, when you make a video call or browse images, AI will detect the video or image in real time, intelligently identify fraud risks, and immediately alert you." Optionally, the interface may also include a control 202, used by the user to confirm whether to participate in the improvement program, so that developers can collect user data and use this data to improve and optimize the recognition algorithm.

[0092] It is understood that the above-mentioned browsing of images may refer to watching videos, watching live video streams, browsing images or videos through social platforms (such as Changlian), browsing images through web pages, or browsing videos or images through other channels. This application does not limit this.

[0093] It is understood that the function of electronic device 200 to identify forged images can also be activated in other ways, such as by voice command, by shortcut gesture or shortcut key, or by other possible methods. This application does not limit this.

[0094] When a user activates the function of identifying forged images on the electronic device 200, the electronic device 200 can perform forgery analysis on one or more objects and / or scenes in the image, and can identify whether a specific object in the image is forged. For example, it can identify whether the person or animal in the image has been face-swapped, whether the part or the whole of the person or animal in the image has been synthesized, whether the scene in the image has been synthesized, and whether the sound associated with the image (such as the sound made by a person in a video) has been synthesized.

[0095] For example, taking a mobile phone as an electronic device, Figure 3 This illustration shows another operational diagram of enabling the function of an electronic device to identify forged images, according to an embodiment of this application. Figure 3 As shown, the function of recognizing forged images of electronic device 300 can be enabled through the system settings of electronic device 300.

[0096] In one example, through the system settings of electronic device 300, the display interface of electronic device 300 can be made to display as follows: Figure 3The interface shown includes setting boxes 301, 302, and 303. Setting box 301 is used to enable or disable the call fraud detection function of electronic device 300. Setting box 301 may also include the explanatory text of setting box 301's function: "When enabled, when you are talking to a stranger, AI will detect the conversation content in real time, intelligently identify fraud risks, and immediately alert you." Setting box 302 is used to enable or disable the video fraud detection function of electronic device 302. Setting box 302 may also include the explanatory text of setting box 302's function: "When enabled, when you are making a video call or watching a video, AI will detect the video frame in real time, intelligently identify fraud risks, and immediately alert you." Setting box 303 is used to enable or disable the fake image detection function of electronic device 303. Setting box 303 may also include the explanatory text of setting box 303's function: "When enabled, when you are browsing images, AI will detect the images in real time, intelligently identify fake images, and immediately alert you."

[0097] When a user activates the call fraud detection function of the electronic device 300, the electronic device 300 can detect the content of the user's conversation during video and voice calls in real time, thereby intelligently identifying fraud risks and issuing real-time alerts.

[0098] When a user activates the video fraud detection function of the electronic device 300, the electronic device 300 can perform forgery analysis on one or more objects and / or scenes in the video displayed on the screen. It can identify whether specific objects in the video are forged, such as whether the people or animals in the video have undergone face swapping, whether the parts or the whole of the people or animals in the video have been synthesized, whether the scenes in the video have been synthesized, and whether the sounds in the video (such as the sounds made by the people in the video) have been synthesized. The video displayed on the screen can be, for example, a live video, a video on a webpage, a video during a video call, a video during a video conference, a video on a social platform, or a video displayed during the operation of other applications. This application does not limit this.

[0099] When a user activates the fake image recognition function of the electronic device 300, the electronic device 300 can perform fake image analysis on one or more objects and / or scenes in the images displayed on the screen. It can identify whether a specific object in the image is fake, such as whether the person or animal in the image has undergone face swapping, whether the part or whole of the person or animal in the image has been composited, and whether the scene in the image has been composited. The image displayed on the screen can be an image on a webpage, an image on a social platform (such as Changlian), or an image displayed during the operation of other applications. This application does not limit this.

[0100] For example, taking a mobile phone as an electronic device, Figure 4 The diagram shows several user interface illustrations illustrating the forgery analysis results of images provided in embodiments of this application.

[0101] like Figure 4 As shown in (a), the display screen of electronic device 410 shows a video call interface, which includes screen 401 and screen 402. Screen 401 is the video screen of the other end, and screen 402 is the video screen of the local end. The video screen of the other end includes multiple objects, including people 4011, clouds 4012, clouds 4013, and houses 4014. Electronic device 410 can perform forgery analysis on screen 401 and screen 402, and can identify whether multiple objects in screen 401 are forged objects, and whether the scene in screen 401 is a forged scene. It can also identify whether one or more elements associated with screen 401 are forged elements. For example, it can identify whether the received sound associated with screen 401 is a forged sound, and whether the received pop-up animation associated with screen 401 is a forged animation.

[0102] When the electronic device 410 identifies the image 401 as a fake image, the electronic device 410 can, for example, display a reminder box 403 on the current video call interface. The reminder box 403 may include the text "The other party is suspected of using AI generation technology, please be cautious!"; for example, the reminder box 403 can further remind the user whether the person or the scene in the image 402 is fake, and can further remind the user which people in the image 402 are fake, more specifically, which elements in the person image are fake, such as hair, eyes, etc., and can specifically remind the user which part of the scene is fake; in addition, the reminder box 403 can also remind the user which elements among one or more elements output with the image 401 are fake, such as the video call sound from the other end device being fake, or the animation that pops up with the video image 402 of the other end being fake.

[0103] In some embodiments, overly beautified images can also be identified as fake images. For example, if an image includes a person and a pet, and the person is overly beautified, the electronic device can alert the user that the person is a fake, specifically by alerting the user that the person is overly beautified.

[0104] In one example, during a video call between user 1 and electronic device 410, AI technology is used to replace user 1's face with user 2's face (i.e., the face of person 4011). Thus, the video call interface of electronic device 400 displays the face of person 4011. Electronic device 410 can perform forgery analysis on image 401, identify that person 4011 is a face-swapped figure, and issue a reminder to the user. This reminder could, for example, alert the user that image 4011 is a forged image, or specifically alert the user that person 4011 in image 401 is a face-swapped figure. For example, the reminder box 403 could include the text "Person 4011 is suspected of using AI face-swapping technology; please verify carefully!"

[0105] In one example, during a video call between user 1 and electronic device 410, AI technology is used to replace user 1 with user 2. Thus, the person displayed on the video call interface of electronic device 410 is user 2 (person 4011). Electronic device 410 can perform forgery analysis on image 401, identify that person 4011 is fake, and issue a reminder message to the user. This reminder message can, for example, remind the user that image 401 is a fake image, or specifically remind the user that person 4011 in image 401 is a fake person. For example, the reminder box 403 may include the text "Person 4011 is suspected to be a fake person, please be cautious!".

[0106] In one example, during a video call between user 1 and electronic device 410, AI technology is used to replace scene 1 with scene 2, which includes clouds 4012, 4013, and a house 4014. Thus, the scene displayed on the video call interface of electronic device 410 is scene 2. Electronic device 410 can perform forgery analysis on image 401, identify that the scene user 1 is in is fake, and issue a reminder message to the user. This reminder message can, for example, remind the user that image 401 is a fake image, or specifically remind the user that the scene user 1 is in in image 401 is fake. More specifically, it can also remind the user of the forgery details of the scene user 1 is in in image 401, such as which part of the scene is fake, whether the scene is AI-generated or composed of multiple real scenes. For example, the reminder box 403 may include the text "Scene 1 is suspected to be a fake scene, please be cautious!".

[0107] In particular, the scene in which user 1 is located in screen 401 is fake. For example, it may include one or more fake objects in the scene, or the arrangement position or order of one or more objects in the scene may be fake, or the entire scene relative to the person in the image may be fake.

[0108] In one example, during a video call between user 1 and electronic device 410, AI technology is used to replace user 1's voice 1 with voice 2. Thus, the voice emitted by electronic device 410 becomes voice 2. Electronic device 410 can perform forgery analysis on voice 2, for example, by combining the video call footage with the forgery analysis of voice 2, identifying that voice 2 is fake, and can issue a reminder message to the user. This reminder message could, for example, be used to remind the user that voice 2 is a fake image. For example, the reminder box 403 could include the text "The voice emitted by person 4011 is suspected to be a fake voice; please be cautious!"

[0109] For example, it can identify that voice 2 is fake by combining the lip movements of the person in the video call interface, or it can identify that voice 2 is fake by combining model analysis.

[0110] It is understandable that the three examples above can be implemented individually or in combination. In other words, electronic devices can simultaneously identify face swaps, fake people, and fake scenes in images, as well as fake elements associated with the image output, and issue alerts to the user.

[0111] It is understandable that reminders to users are not limited to reminder boxes; they can also be sent to users by displaying reminder icons, live windows, or cards.

[0112] In one example, when a user enters the video call interface, a live feed window can be displayed. This window may display text such as "Click here to enable AI forgery detection." Upon clicking the live feed window, the electronic device begins AI forgery detection, displaying text such as "AI forgery detection protection in progress." When the electronic device detects that the other end's image is a forged image, the live feed window may display text such as "Suspected AI forgery." More specifically, more granular alerts can be displayed. For example, if the device detects that the person in the other end's image has undergone face swapping, the live feed window can alert the other end that it is suspected of AI face swapping; another example is that if the scene in the other end's image is detected as a composite scene, the live feed window can alert the other end that it is suspected of using AI-generated scenes; yet another example is that if the audio output associated with the other end's image is a composite audio or the audio does not match the lip movements of the person in the other end's image, the live feed window can alert the other end that it is suspected of using forged audio.

[0113] In some embodiments, when a user enters a video call interface, a live window can be displayed on the video call interface. The live window may display text such as "Click here to enable AI forgery detection". If the user does not click the live window within a preset time, the electronic device can cancel the display of the live window on the video call interface.

[0114] In one example, when a user enters the video call interface, based on the user's preset settings, the electronic device can automatically activate AI forgery detection on the video screen. The electronic device can display a live window on the video call interface, which may display the text "AI forgery detection protection in progress." When the electronic device detects that the other end's image is a forged image, the live window may display the text "Suspected AI forgery." More specifically, it can display more granular reminders. For example, if it detects that the image of a person in the other end's image has been face-swapped, it can remind the other end that it is suspected of AI face-swapping. Another example is that if it detects that the scene in the other end's image is a composite scene, it can remind the other end that it is suspected of using AI-synthesized scenes. Yet another example is that if it detects that the audio output associated with the other end's image is a composite audio or the audio does not match the lip movements of the person in the other end's image, it can remind the other end that it is suspected of using forged audio.

[0115] In some embodiments, the above-described live view window may be replaced by a service card display.

[0116] In some embodiments, when the electronic device 410 identifies the screen 401 as a fake screen, the electronic device 410 may also remind the user by means of voice, vibration or other means. This application does not limit the method of reminding the user.

[0117] like Figure 4 As shown in (b), the display screen of the electronic device 420 shows a chat interface, which includes an image 404 sent by other users. The image 404 includes multiple objects, including a person 4041 and a row of seats 4042. The electronic device 420 can perform forgery analysis on the image 404, and can identify whether multiple objects in the image 404 are forged objects, and whether the scene of the image 404 is a forged scene. It can also identify whether one or more elements associated with the image 404 are forged elements, such as identifying whether the pop-up animation received and associated with the image 404 is a forged animation.

[0118] Furthermore, when image 404 is identified as a forged image, electronic device 420 can issue a reminder to the user. For example, electronic device 420 can issue a reminder to the user by displaying a reminder box in the current chat interface, or by issuing a reminder to the user through voice, vibration, or other means. The reminder box may include text such as "This image is suspected of being generated using AI technology. Please be cautious!" The reminder box can also be used to more specifically remind the user which objects and / or scenes in the image are forged.

[0119] It is understandable that reminders to users are not limited to reminder boxes; they can also be given reminders through live windows or cards.

[0120] In one example, after the electronic device displays a chat interface, a live feed window can be displayed on that interface. This live feed window may display text such as "Click here to enable AI forgery detection." Upon the user clicking the live feed window, the electronic device begins AI forgery detection on images received and / or sent in the chat interface. This live feed window may display text such as "AI forgery detection protection in progress." For example, when the electronic device detects that a received image is a forgery, the live feed window may display text such as "Suspected AI forgery." More specifically, more granular alerts can be displayed. For example, if a received image is detected to have undergone face-swapping, the live feed window can alert the user that the received image is suspected of being AI-generated. Similarly, if a received image is detected to be a composite scene, the live feed window can alert the user that the scene is suspected of being AI-generated. Furthermore, the live feed window can specifically alert the user which objects and / or scenes in the image are forged.

[0121] In some embodiments, after the electronic device displays a chat interface, a live window can be displayed on the chat interface. The live window may display text such as "Click here to enable AI forgery detection". If the user does not click the live window within a preset time, the electronic device can cancel the display of the live window on the chat interface.

[0122] In one example, after the electronic device displays a chat interface, based on the user's preset settings, the device can automatically enable AI forgery detection for received and / or sent images. The electronic device can display a live view window in the chat interface, which may display text such as "AI forgery detection protection in progress." For example, when the electronic device detects that a received image is a forged image, the live view window may display text such as "Suspected AI forgery." More specifically, it can display more granular reminders. For example, if it detects that the portrait in the received image has been face-swapped, it can remind the user that the received image is suspected of being AI face-swapped. Another example is that if it detects that the scene in the received image is a composite scene, it can remind the user that the scene in the received image is suspected of being an AI composite scene. Yet another example is that if it detects that the animation that pops up with the received image is a forged animation, it can remind the user that the associated pop-up animation is a forged animation.

[0123] In some embodiments, the above-described live view window may be replaced by a service card display.

[0124] In some embodiments, when the interface of the electronic device displays a preview of a large image, the electronic device prompts the user whether AI forgery detection is required or the electronic device automatically enables AI forgery detection.

[0125] like Figure 4 As shown in (c), the display screen of the electronic device 430 displays an information interface, which includes an image 405 sent by other users. The image 405 includes multiple objects, including a person 4051 and a row of seats 4052. The electronic device 430 can perform forgery analysis on the image 405, and can identify whether multiple objects in the image 405 are forged objects, and whether the scene of the image 405 is a forged scene. It can also identify whether one or more elements associated with the image 405 are forged elements, such as identifying whether the pop-up animation received and associated with the image 405 is a forged animation.

[0126] Furthermore, when image 405 is identified as a forged image, electronic device 430 can issue a reminder to the user. For example, electronic device 430 can issue a reminder to the user by displaying a reminder box in the current chat interface, or by issuing a reminder to the user through voice, vibration, or other means. The reminder box may include text such as "This image is suspected of being generated using AI technology. Please be cautious!" More specifically, it can also remind the user which objects and / or scenes in image 405 are forged.

[0127] It is understandable that reminders to users are not limited to reminder boxes; they can also be given reminders through live windows or cards.

[0128] In some embodiments, when the interface of the electronic device displays a preview of a large image, the electronic device prompts the user whether AI forgery detection is required or the electronic device automatically enables AI forgery detection.

[0129] like Figure 4 As shown in (d), the screen of electronic device 440 displays a webpage, which includes images 406 and 407. Image 406 includes multiple objects, such as a person 4061, a cloud 4062, a cloud 4063, and a house 4064. Image 407 includes multiple objects, such as a person 4071 and a row of seats 4072. Electronic device 440 can perform forgery analysis on images 406 and 407, and can identify whether multiple objects in image 406 are forged objects, and whether the scene in image 406 is a forged scene. It can also identify whether multiple objects in image 407 are forged objects, and whether the scene in image 407 is a forged scene. Furthermore, it can identify whether one or more elements associated with image 407 are forged elements, such as whether a pop-up animation associated with image 405 is a forged animation.

[0130] Furthermore, when image 406 is identified as a forged image, electronic device 440 can issue a reminder to the user. For example, electronic device 440 can issue a reminder to the user by displaying a reminder box in the current chat interface, or by issuing a reminder to the user through voice, vibration, or other means. The reminder box may include text such as "This image is suspected of being generated using AI technology. Please be cautious!" More specifically, it can also remind the user which objects and / or scenes in image 406 are forged.

[0131] It is understandable that reminders to users are not limited to reminder boxes; they can also be given reminders through live windows or cards.

[0132] In some embodiments, when the interface of the electronic device displays a preview of a large image, the electronic device prompts the user whether AI forgery detection is required or the electronic device automatically enables AI forgery detection.

[0133] like Figure 4 As shown in (e), the display screen of the electronic device 450 shows an image browsing interface, which includes multiple images, and the electronic device 450 can perform forgery analysis on these multiple images.

[0134] Furthermore, when image 408 in the multiple images is identified as a forged image, electronic device 450 can issue a reminder to the user. For example, electronic device 450 can issue a reminder to the user by displaying a reminder box in the current chat interface, or by issuing a reminder to the user through voice, vibration, or other means. The reminder box may include text such as "This image is suspected of being generated using AI technology. Please be cautious!" More specifically, it can also remind the user which objects and / or scenes in image 408 are forged.

[0135] It is understandable that reminders to users are not limited to reminder boxes; they can also be given reminders through live windows or cards.

[0136] like Figure 4 As shown in (f), if the electronic device 460 recognizes during a call that the voice of the other end user received on its own device is fake or that the video of the other end user displayed on its own device is fake, then after the call ends, the call can be marked as fake in the corresponding call log.

[0137] It should be understood that, Figure 4 The embodiments shown are illustrated using video call scenarios, chat scenarios, messaging scenarios, web browsing scenarios, and image browsing scenarios as examples. However, this does not limit the application scenarios of the embodiments of this application. The method for identifying forged images provided by the embodiments of this application can perform forgery analysis on any video or image displayed on the screen of an electronic device in any form. For example, it can also be applied to video live streaming scenarios.

[0138] In some embodiments, the electronic device can detect an image displayed on its screen and perform forgery analysis on the displayed image.

[0139] In some embodiments, when an image is detected on the screen of an electronic device, the electronic device may ask the user whether to perform forgery analysis on the displayed image. If the user selects to perform forgery analysis on the displayed image, the electronic device performs forgery analysis on the displayed image.

[0140] In some embodiments, when an image is displayed on the screen of an electronic device, forgery analysis can be performed on the displayed image based on a user-triggered operation.

[0141] For example, taking a mobile phone as an electronic device and a video call scenario as an example, Figure 5 This illustration shows an operation diagram of triggering forgery analysis of an image according to an embodiment of this application.

[0142] like Figure 5As shown in (a), the screen of the electronic device 500 displays a video call interface, which includes screen 501 and screen 502. Screen 501 is the video screen of the other end, and screen 502 is the video screen of the local end. The video screen of the other end includes multiple objects, including a person 5011, a cloud 5012, a cloud 5013, and a house 5014.

[0143] When the electronic device 500 detects that screens 501 and 502 are displayed on the screen, it can display a reminder box 503 on the current interface. The reminder box 503 is used to remind the user whether to perform spoofing analysis on screens 501 and 502. The reminder box 503 also includes controls for "yes" and "no". When the user selects the control for "yes", the electronic device 500 performs spoofing analysis on screens 501 and 502.

[0144] like Figure 5 As shown in (b), when the electronic device 500 identifies that the image 501 is a fake image, the electronic device 500 may, for example, display a reminder box 504 in the current video call interface. The reminder box 504 may include the text "The other party is suspected of using AI generation technology, please be cautious!"; for example, the reminder box 504 may further remind the user whether the person or the scene in the image 501 is fake, and may also more specifically remind the user which objects in the image 501 are fake objects, and / or which part of the scene in the image 501 is a fake scene, and / or which elements output in association with the image 501 are fake elements. The reminder box 504 may include the text "The hair of person 5011 is suspected of using AI generation technology, please be cautious!".

[0145] In some embodiments, the user drags the image to be forged and analyzed to the interactive area of ​​the electronic device, or the user selects the image to be forged and analyzed on the display screen of the electronic device, or the user performs a touch operation on the control displayed on the display screen that triggers the electronic device to identify the image to be forged and analyzed, so that the electronic device enters the instruction receiving state; then the user inputs an instruction to the electronic device to instruct the image to be forged and analyzed; thereby causing the electronic device to perform forged and analyzed image.

[0146] The user can input instructions to the electronic device to perform forgery analysis on the image that needs to be forged. This can include inputting voice instructions, inputting instructions by text, or inputting instructions by clicking on the corresponding control. This application does not limit the scope of these methods.

[0147] For example, taking a mobile phone as an electronic device and a video call scenario as an example, Figure 6This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0148] like Figure 6 As shown in (a), the display screen of the electronic device 600 displays a video call interface, which includes screen 601 and screen 602. Screen 601 is the video screen of the other end, and screen 602 is the video screen of the local end. The video screen of the other end includes multiple objects, including a person 6011, a cloud 6012, a cloud 6013, and a house 6014.

[0149] When a user wants to know whether screen 601 and / or screen 602 are fake images, the user can perform a touch operation on the touch bar (AI BAR) 603 displayed in the video call interface. Based on the user's touch operation, the electronic device 600 can perform forgery analysis on screen 601 and / or screen 602. For example, it can identify whether multiple objects in screen 601 are fake objects, and whether the scene in screen 601 is a fake scene. It can also identify whether one or more elements received and output in association with screen 601 are fake elements. For example, it can identify whether the sound received and output in association with screen 601 is a fake sound, and it can also identify whether the pop-up animation received and output in association with screen 601 is a fake animation.

[0150] In some embodiments, forgery analysis of screen 601 and / or screen 602 can be triggered by touch bar 603 and voice function of electronic device 600 (e.g., Xiaoyi voice).

[0151] In some embodiments, when a user triggers a forgery detection of screen 601 and / or screen 602, the electronic device 600 can prompt the user on the video call interface that it is currently under AI forgery detection protection.

[0152] like Figure 6 As shown in (b), when the image 601 is identified as a forged image, the electronic device 600 can issue a reminder to the user. For example, the electronic device 600 can issue a reminder to the user by displaying a reminder box 604, a live window, or a card in the video call interface. It can also issue a reminder to the user by voice, vibration, etc. The reminder text can be, for example, "The other party is suspected of using AI generation technology. Please be cautious!" The reminder box can also further remind the user whether the person or the scene in the image 601 is forged. It can also more specifically remind the user which objects in the image 601 are forged objects, and / or which part of the scene in the image 601 is a forged scene, and / or which elements output in association with the image 601 are forged elements.

[0153] For example, taking a mobile phone as an electronic device and a video call scenario as an example, Figure 7 This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0154] like Figure 7 As shown in (a), the display screen of the electronic device 700 displays a video call interface, which includes screen 701 and screen 702. Screen 701 is the video screen of the other end, and screen 702 is the video screen of the local end. The video screen of the other end includes multiple objects, which may include people, clouds, and houses.

[0155] When the electronic device 700 detects that a video call interface has been entered, a live window 703 can be displayed on the video call interface. The live window 703 can serve as the entry point for the user to enable AI forgery detection. For example, the live window can display the text "Click to enable AI forgery detection".

[0156] When a user wants to know whether images 701 and / or 702 are forged, the user can click on the live view window 703 to trigger the electronic device to perform AI forgery detection on images 701 and / or 702 in real time during the video call. At this time, the video call interface of the electronic device 700 can be seen as follows: Figure 7 The interface shown in (b) can display, for example, the text "AI forgery detection protection in progress" in the live window 703, to remind the user that AI forgery detection is being performed on the video call screen in real time.

[0157] For example, when the electronic device 700 detects that the screen 701 is a fake image, the electronic device 700 can issue a reminder to the user through the live window 703. For example, it can specifically remind the user whether the person or the scene in the screen 701 is fake, or it can more specifically remind the user which objects in the screen 701 are fake objects, and / or which part of the scene in the screen 701 is a fake scene, and / or which elements output in association with the screen 701 are fake elements.

[0158] For example, such as Figure 7 As shown in (c), when it is detected that the image in screen 701 is a face-swapped image, the live window 703 may display the text "The other party is suspected of AI face swapping".

[0159] In some embodiments, after the electronic device 700 is triggered to perform AI forgery detection, a reminder message “To turn it off, please turn it off at the ××× path” can be displayed in the video call interface in conjunction with the live window, so that the user can quickly turn off the AI ​​forgery detection.

[0160] In some embodiments, when the electronic device 700 detects that it has entered the video call interface, the electronic device automatically triggers AI forgery detection on the screen 701 and / or screen 702 in real time during the video call, and can display a live window 703 on the video call interface. The live window 703 may display the text "AI forgery detection protection in progress" to remind the user that AI forgery detection is being performed on the video call screen in real time.

[0161] For example, taking a mobile phone as an electronic device and web browsing as an example, Figure 8 This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0162] like Figure 8 As shown in (a), the display screen of the electronic device 800 displays a webpage, which includes images 801 and 802. Image 801 includes multiple objects, such as a person 8011, a cloud 8012, a cloud 8013, and a house 8014. Image 802 includes multiple objects, such as a person 8021 and a row of seats 8022.

[0163] When a user wants to know whether image 801 is a fake image, the user can perform a trigger operation on image 801 (such as long-pressing image 801), causing the current interface of the electronic device to display an option box 803 associated with image 801. The option box 803 includes the option "Fake Analysis", and may also include options such as "Save" and "Copy". Based on the user's further click on the option "Fake Analysis", the electronic device 800 performs fake analysis on image 801. Through the fake analysis of image 801, the electronic device 800 can identify whether multiple objects in image 801 are fake objects, whether the scene of image 801 is a fake scene, and whether the pop-up animation received and output associated with image 801 is a fake animation.

[0164] like Figure 8 As shown in (b), when image 801 is identified as a forged image, electronic device 800 can issue a reminder to the user. For example, electronic device 800 can issue a reminder to the user by displaying a reminder box in the current chat interface, or by issuing a reminder to the user through voice, vibration, etc. The reminder box may include text such as "This image is suspected of being generated using AI technology, please be careful!", or it may further remind the user whether the person or the scene in image 801 is forged, or more specifically remind the user which objects in image 801 are forged objects, and / or which part of the scene in image 801 is a forged scene, and / or which elements output associated with image 801 are forged elements.

[0165] For example, taking a mobile phone as an electronic device and web browsing as an example, Figure 9 This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0166] like Figure 9 As shown, the display screen of electronic device 900 shows a webpage, which includes image 901.

[0167] When a user wants to know whether image 901 is a fake image, the user can drag image 901 to activate the voice function of the electronic device and drag image 901 into dialog box 902. At this time, the electronic device 900 can ask the user how to process the image in the dialog box 902. For example, the user can input the command "Help me identify whether this image is fake" by touching the voice control 903. Based on the command, the electronic device begins to perform AI forgery detection on image 902. Correspondingly, the dialog box 902 can display the text "AI forgery intelligent detection in progress...".

[0168] It is understood that this application embodiment uses web page browsing image as an example, but this does not limit the use scenario of this embodiment. For example, images in the chat interface can also be dragged into the dialog box, and image forgery detection can be triggered by voice commands.

[0169] For example, taking a mobile phone as an electronic device and web browsing as an example, Figure 10 This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0170] like Figure 10 As shown in (a), the display screen of the electronic device 1000 shows a large preview interface of image 1001, which includes two trees and a puppy.

[0171] When a user wants to know whether the puppy in image 1001 is a fake, the user can select the puppy in image 1001. Based on the user's selection, the voice function of electronic device 1000 is activated, and a voice recognition box 1003 can be displayed on the interface of electronic device 1000. This voice recognition box 1003 may display, for example, guiding text such as "Ask about the selected object on the screen." Furthermore, the user can perform a touch operation on the voice control 1002 and issue a voice command, "Help me identify whether this dog is fake," switching the display interface of electronic device 1000 to, for example,... Figure 10The interface shown in (b) shows the text "Help me identify if this dog is fake" displayed in the voice recognition box 1003; furthermore, the electronic device begins to perform forgery detection on the dog image selected by the user, and the display interface of the electronic device 1000 can be switched to the interface shown in (b). Figure 10 The interface shown in (c) displays a dialog box 1004, which shows the image of the puppy selected by the user, the user's voice command "Help me identify whether this dog is fake", and the feedback text from the electronic device 1000 "AI fake detection in progress...".

[0172] It is understood that this application embodiment uses a large image preview interface as an example, but this does not limit the usage scenario of this embodiment. For example, images in a web browsing interface can be selected, and image forgery detection can be triggered by voice commands.

[0173] For example, taking a mobile phone as an electronic device and web browsing as an example, Figure 11 This illustration shows another operational diagram of triggering image forgery analysis provided in an embodiment of this application.

[0174] like Figure 11 As shown in (a), the display screen of the electronic device 1100 shows a large preview interface of image 1101, which includes a puppy 1102 and a human figure 1103; the interface also shows a touch bar 1104, which is used to trigger AI forgery detection of image 1101.

[0175] When a user wants to know whether image 1101 is a fake object, the user can perform a touch operation on the touch bar 1104. Based on the user's touch operation, the electronic device identifies the objects in image 1101 and identifies the puppy 1102 and the human figure 1103.

[0176] like Figure 11 As shown in (b), the user can further activate the voice function of the electronic device 1100 and trigger the electronic device to perform forgery detection on the puppy 1102 and the human figure 1103 by issuing a voice command. At this time, a voice recognition box 1105 is displayed on the interface of the electronic device 1100. The voice recognition box is used to display the user's voice command recognized by the electronic device 1100. For example, the voice command issued by the user is, for example, "Xiao Yi Xiao Yi, help me identify whether these objects are forged."

[0177] Based on the user's voice commands, the display interface of electronic device 1100 can be switched to, for example... Figure 11The interface shown in (c) displays a dialog box 1106, which shows the identified puppy image 1102 and human image 1103, the user's voice command "Xiaoyi Xiaoyi, help me identify whether these objects are fake", and the feedback text from the electronic device 1100 "AI fake detection in progress...".

[0178] It is understood that this application embodiment uses a large image preview interface as an example, but this does not limit the use scenario of this embodiment. For example, it can also recognize images in a web browsing interface and trigger image forgery detection through voice commands.

[0179] In some embodiments, when multiple objects (e.g., multiple faces) are identified in an image, the forgery detection results output by the electronic device may specifically include multiple detection results corresponding to each of the multiple objects.

[0180] For example, taking a mobile phone as an electronic device and an information viewing interface as an example, Figure 12 This illustration shows a schematic diagram of an interface for displaying forgery analysis results provided in an embodiment of this application.

[0181] like Figure 12 As shown, the electronic device 1200 displays an information interface on its screen, which includes an image 1201 sent by other users. The electronic device 1200 can perform forgery analysis on the image 1201, and can identify whether multiple objects in the image 1201 are forged objects, and can identify whether the scene in the image 1201 is a forged scene.

[0182] Furthermore, when image 1201 is identified as a forged image, electronic device 1200 can issue a reminder to the user. For example, electronic device 1200 can issue a reminder to the user by displaying a reminder box, live window, or card in the current chat interface, or by issuing a reminder to the user via voice, vibration, etc. The reminder box may include text such as "This image is suspected of being generated using AI technology, please be cautious!", and may further remind the user whether the person or scene in image 1201 is forged, or more specifically remind the user which objects in image 1201 are forged objects, and / or which part of the scene in image 1201 is a forged scene, and / or which elements output associated with image 1201 are forged elements.

[0183] In some embodiments, after detecting that image 1201 is a forged image, in addition to issuing a relevant reminder to the user, the system can also provide the user with an entry point for subsequent operations, such as providing the user with an entry point for interception operations. Figure 12The control 1203 in the option box 1202 shown, for example, provides an entry point for the user to report operations, such as... Figure 12 Control 1204 in option box 1202 shown.

[0184] In some embodiments, after detecting that the image associated with the bank account is a forged image, if the electronic device continues to detect that the user has started to perform the related transfer operation, the electronic device may, for example, add multi-factor authentication to the transfer operation, or give the user one or more key reminders, or the electronic device may freeze the current operation interface, so that the current user's interaction operation is invalid.

[0185] For example, Figure 13 A schematic flowchart of a method 1300 for identifying forged images according to an embodiment of this application is shown. Figure 13 As shown, the method 1300 includes:

[0186] S1301: When a first image is displayed on the screen of an electronic device, a forgery analysis is performed on the first image.

[0187] In some embodiments, forgery analysis of the first image includes forgery analysis of one or more objects in the first image, and / or, forgery analysis of a scene in the first image, and / or, forgery analysis of one or more elements of an output associated with the first image.

[0188] One or more elements associated with the first image output may include, for example, sound and / or pop-up animation.

[0189] In some embodiments, when a first image is detected to be displayed on the screen of an electronic device, a forgery analysis is performed on the first image using a first model.

[0190] More specifically, it is detected that the first image is displayed on the screen of the electronic device, for example, it could be detected that the first image is displayed on the interface of the first application.

[0191] The first application could be, for example, a video playback application, a live video streaming application, a video call application, a browser application, or a social application (such as Changlian).

[0192] In one implementation, when the first application is detected to be running, the electronic device begins to detect in real time whether the interface of the first application displays the first image, and performs spoofing analysis on it when the first image is detected to be displayed.

[0193] The first image may include pictures and / or videos, such as videos displayed by an electronic device while running a video call application, live videos displayed by an electronic device while running a live streaming application, pictures displayed by an electronic device while running a social media application or a browser application, or pictures displayed by an electronic device while running a gallery application.

[0194] In some embodiments, before S1301 is executed, the electronic device needs to obtain the corresponding application permissions. For example, after obtaining the corresponding permissions for the video call application, the electronic device can detect the images displayed in the video call interface during the operation of the video call application and perform forgery analysis on the detected images.

[0195] In some embodiments, when the first image is a video, a forgery analysis is performed on the first image. The specific process may include: first obtaining the video frame corresponding to the video, and then performing forgery analysis on one or more objects in the video frame, the sound of the video, and the scene in the video frame.

[0196] The objects in the first image may include, for example, one or more people, animals, or objects.

[0197] The scene in the first image can be relative to the first image as a whole, for example, it can refer to the scene where a person or animal is located.

[0198] The explanation of the first model will be detailed in subsequent embodiments, and will not be described in detail here.

[0199] S1302: When the electronic device identifies that there is a forged object in one or more objects in the first image and / or that the scene of the first image is a forged scene and / or that there is a forged element in one or more elements output with the first image, the electronic device issues a first reminder to the user, the first reminder being used to mark the forged object and / or forged scene and / or forged element present in the first image.

[0200] In other words, the first reminder is used to remind the user which objects in the first image are fake objects, and / or the first reminder is used to remind the user which part of the scene in the first image is a fake scene, and / or the first reminder is used to remind the user which elements in the output associated with the first image are fake elements.

[0201] It is understandable that there can be multiple ways in which the first reminder mark contains forged objects and / or forged scenes and / or forged elements in the first image.

[0202] In some examples, the labels can be descriptive, for example: electronic devices can label fake objects and / or fake scenes and / or fake elements in the first image by displaying reminder text on the screen, which indicates which objects in the first image are fake objects and / or which scenes are fake scenes and / or which associated output elements are fake elements.

[0203] In some examples, forgery objects and / or forgery scenes and / or forgery elements can be marked by selecting them. For example, an electronic device marks forgery objects and / or forgery scenes and / or forgery elements in a first image by selecting forgery objects and / or forgery scenes and / or forgery elements in the first image on a display screen. This indicates which objects in the first image are forgery objects and / or which scenes are forgery scenes and / or which associated output elements are forgery elements. The selection method may include, for example, circling.

[0204] In some examples, the location of the fake object and / or fake scene and / or fake element in the first image can be marked with a hint symbol, which may include, for example, a yellow or red exclamation mark, a yellow or red triangle icon, etc.

[0205] In some examples, the forgery can be marked by voice prompts, for example, when an electronic device issues a voice prompt to indicate which objects in the first image are forged objects and / or which scenes are forged scenes and / or which associated output elements are forged elements, thus marking the forged objects and / or forged scenes and / or forged elements present in the first image.

[0206] In addition, the first reminder may also mark the forged objects and / or forged scenes and / or forged elements present in the first image in other ways, which is not limited in this application.

[0207] The elements associated with the first image may include, for example, sound and / or pop-up animation, as well as other associated output elements, such as pop-up text.

[0208] In one example, the first image is a video, and the elements associated with the first image may include the video audio associated with the first image.

[0209] In some embodiments, one or more objects may contain forged objects. For example, a person in the first image may be a forged person, an animal in the first image may be a forged animal, or an item in the first image may be a forged item. Forged persons may refer to a person who is entirely AI-generated virtual, a person whose face has been swapped, or other facial features of the person who has been forged. Similarly, forged animals may refer to an animal that is entirely AI-generated virtual, an animal whose face has been swapped, or other facial features of the animal that have been forged. Forged items may refer to an item that is entirely AI-generated virtual, or an item whose partial features have been forged.

[0210] In some embodiments, the scene in the first image is a fake scene. For example, it may mean that the entire image is a virtual image generated by AI, or that the scene in which the person in the image is located is fake in whole or in part. For example, the real scene is replaced with another scene, and / or scene elements are added or removed in the real scene, and / or the position or relative order of multiple scene elements in the real scene is changed, etc.

[0211] In this embodiment, the electronic device can identify artificial intelligence generated content (AIGC) in the entire image. It can identify both overall forged images and partially forged images. In other words, it can not only perform face-swapping recognition on people in the image, but also perform forged recognition on other parts of people in the image and / or scenes in the image. It can perform more comprehensive forged analysis of the image, thereby effectively identifying forged images and promptly alerting users. This reduces the probability of criminals succeeding in committing online fraud using applications such as video calls, live video streaming, and social media. It can also effectively curb the spread of online public opinion, thereby improving the security of users' Internet use.

[0212] Furthermore, the method provided in this application embodiment enables unified monitoring, forgery analysis, and alerts for images displayed during the operation of multiple applications by electronic devices through application authorization, without requiring application adaptation.

[0213] For example, Figure 14 A schematic flowchart of another method 1400 for identifying forged images provided in an embodiment of this application is shown. Figure 14 As shown, the method 1400 includes:

[0214] S1401: When the first image is displayed on the screen of the electronic device, the electronic device issues a second reminder to the user, which is used to remind the user whether the first image has been subjected to forgery analysis.

[0215] More specifically, the first image is displayed on the screen of an electronic device, for example, the first image may be displayed on the interface of a first application of the electronic device, wherein the first application may be, for example, a video playback application, a live video application, a video call application, a browser application, a social application (e.g., Changlian), etc.

[0216] In one implementation, when the first application is running, the electronic device begins to detect in real time whether the interface of the first application displays the first image, and issues a second reminder to the user when the first image is detected to be displayed.

[0217] The interpretation of the first image has already been... Figure 13 The embodiment shown in S1301 is described in detail, and will not be repeated here for the sake of brevity.

[0218] In some embodiments, the electronic device may issue a second reminder to the user, for example, by displaying a reminder box associated with the first image on the interface, or by issuing a second reminder to the user through voice instructions, etc. This application does not limit the manner in which the second reminder is issued.

[0219] In addition to issuing a second reminder to the user, the electronic device can also provide the user with an entry point to confirm the forgery analysis of the first image.

[0220] S1402: Based on user confirmation, the electronic device performs forgery analysis on the first image.

[0221] In some embodiments, forgery analysis of the first image includes forgery analysis of one or more objects in the first image, and / or, forgery analysis of a scene in the first image, and / or, forgery analysis of one or more elements of an output associated with the first image.

[0222] In some embodiments, based on user confirmation, the electronic device performs forgery analysis on the first image using a first model.

[0223] In some embodiments, the electronic device may display a confirmation control on the interface, and the user may confirm the forgery analysis of the first image by clicking the confirmation control; the user may also confirm the forgery analysis of the first image by issuing a confirmation voice command; the user may also confirm the forgery analysis of the first image in other ways, such as performing a specific gesture, triggering a specific button, etc., which are not limited in this application.

[0224] For further explanation of this step, please refer to [link / reference]. Figure 13 The explanation of S1301 in the illustrated embodiment will not be repeated here for the sake of brevity.

[0225] S1403: When the electronic device recognizes that the first image is a fake image, the electronic device issues a first reminder to the user.

[0226] For an explanation of this step, please refer to [link / reference]. Figure 13 The explanation of S1302 in the illustrated embodiment will not be repeated here for the sake of brevity.

[0227] This method 1400 can be applied to video scenarios such as video calls and live video streaming.

[0228] In this embodiment, the electronic device can proactively ask the user whether to perform forgery analysis on the image when it detects an image displayed on the screen, without requiring the user to initiate the process. Furthermore, the method provided in this embodiment can not only perform face-swapping recognition on people in the image, but also perform forgery recognition on other parts of the people in the image and / or the scene in the image. It can perform more comprehensive forgery analysis on the image at both the overall and local levels, thereby effectively identifying forged images and promptly alerting the user. This reduces the probability of criminals succeeding in using AI technology to commit online fraud and can also effectively curb the spread of online public opinion, thereby improving the security of users' internet use.

[0229] For example, Figure 15 A schematic flowchart of another method 1500 for identifying forged images provided in an embodiment of this application is shown. Figure 15 As shown, this method is applied to an electronic device, where a first image is displayed on the screen of the electronic device. The method 1500 includes:

[0230] S1501: When a first image is displayed on the screen of an electronic device, the electronic device performs a forgery analysis on the first image based on the user's first operation on the first image.

[0231] In some embodiments, forgery analysis of the first image includes forgery analysis of one or more objects in the first image, and / or, forgery analysis of a scene in the first image, and / or, forgery analysis of one or more elements of an output associated with the first image.

[0232] In some embodiments, based on a user's first operation on a first image, the electronic device performs forgery analysis on the first image using a first model.

[0233] The first operation performed by the user on the first image refers to the operation that triggers the forgery analysis of the first image. This first operation could be, for example, a user long-pressing the first image to display a trigger control on the current interface and clicking the trigger control; a user issuing a voice command to perform forgery analysis of the first image; a user activating the voice function of the electronic device by dragging the first image and issuing a voice command to perform forgery analysis of the first image; a user activating the voice function of the electronic device by selecting the first image and issuing a voice command to perform forgery analysis of the first image; a user activating the voice function of the electronic device by touching a touch bar displayed on the same interface as the first image and issuing a voice command to perform forgery analysis of the first image; a user performing a specific gesture to trigger the forgery analysis of the first image; or other possible specific gestures to trigger the forgery analysis of the first image, which this application does not limit.

[0234] For example, the first operation can also be an operation in which the user drags the first image to the interactive area of ​​the electronic device and then inputs a first command to the electronic device; the first operation can also be an operation in which the user selects the first image on the display screen of the electronic device and then inputs a first command to the electronic device, wherein the method of selecting the first image can include, for example, circling, clicking, underlining, long pressing, etc.; the first operation can also be an operation in which the user performs a touch operation on the first control and then inputs a first command to the electronic device, wherein the first control and the first image are displayed on the same interface, and the first command is used to instruct the forgery analysis of the first image.

[0235] In some embodiments, the first operation may be, for example, clicking a second control, which may be a live window or a card.

[0236] S1502: When the electronic device identifies that there is a forged object in one or more objects in the first image and / or that the scene of the first image is a forged scene and / or that there is a forged element in one or more elements output with the first image, the electronic device issues a first reminder to the user, the first reminder being used to mark the forged object and / or forged scene and / or forged element present in the first image.

[0237] For an explanation of this step, please refer to [link / reference]. Figure 13 The explanation of S1302 in the illustrated embodiment will not be repeated here for the sake of brevity.

[0238] This method can be applied to scenarios such as browsing news, web pages, and social applications.

[0239] In this embodiment of the application, when an image is displayed on the screen of an electronic device, the image can be analyzed for forgery based on the user's active triggering operation. Furthermore, the method provided in this embodiment of the application can not only perform face-swapping recognition on people in the image, but also perform forgery recognition on other parts of people in the image and / or scenes in the image. It can perform more comprehensive forgery analysis on the image at both the overall and local levels, thereby effectively identifying forged images and promptly alerting users, reducing the probability of criminals succeeding in using AI technology to commit online fraud, and effectively curbing the spread of online public opinion, thereby improving the security of users' use of the Internet.

[0240] For example, Figure 16 A schematic flowchart of a method 1600 for training a first model for image forgery analysis, according to an embodiment of this application, is shown. Figure 16 As shown, the method 1600 includes:

[0241] S1600: The first model is obtained by training the model based on multiple images and the forgery analysis information of these multiple images.

[0242] The first model takes an image as input and outputs forgery analysis information of the image.

[0243] The forgery analysis information of the multiple images includes information on whether the scene in the image is a forged scene, information on whether one or more objects in the image are forged objects, and information on whether one or more elements associated with the image output are forged elements. The one or more elements associated with the image output may include, for example, sound and / or pop-up animation and / or pop-up text.

[0244] For example, the multiple images include video 1, and the forgery analysis information of video 1 includes information for indicating whether the scene in video 1 is a forged scene, and may further include information for indicating whether one or more objects in video 1 are forged objects, and may further include information for indicating whether the sound output associated with video 1 is a forged sound.

[0245] In this embodiment of the application, a model can be trained based on multiple images and the forgery analysis information of the multiple images to obtain a model that can be used for image forgery analysis. Since the images used for model training include images of known forged scenes, the trained model can identify scene forgeries in the images.

[0246] For example, taking video calls and live video streaming scenarios as examples, Figure 17 This illustration shows a system architecture diagram for video forgery analysis provided in an embodiment of this application.

[0247] like Figure 17 As shown, the system architecture includes a live video streaming application and a video call application, as well as a monitoring module 1710, an image acquisition module 1720, and a forgery analysis module 1730. The image acquisition module 1720 includes a display frame 1721, a video processing module 1722, and a video frame processing module 1723. Specifically:

[0248] The monitoring module 1710 is used to monitor whether the video live streaming application has started live streaming, and to monitor whether the video call application has started video call.

[0249] The monitoring module 1710 is also used to send a video start message to the image acquisition module when it detects that a video live streaming application has started video live streaming, and it is also used to send a video start message to the image acquisition module when it detects that a video call application has started video call.

[0250] Display frame 1721 can be used to display prompt information 1 to the user, prompting the user whether to perform spoofing analysis on the video screen of the live video application and / or the video screen of the video call application; display frame 1721 can also be used to display control 1, which is used by the user to confirm that the video screen of the live video application and / or the video screen of the video call application has been spoofed.

[0251] The video processing module 1722 is used to obtain the video from the live video application and process the obtained video to obtain the corresponding video frame after the user confirms the forgery analysis of the video screen of the live video application; it is also used to obtain the video from the video call application and process the obtained video to obtain the corresponding video frame after the user confirms the forgery analysis of the video screen of the video call application.

[0252] For example, you can obtain videos from a live video streaming application and / or from a video calling application.

[0253] The video processing module 1722 is also used to send video frames to the video frame processing module 1723.

[0254] The video frame processing module 1723 is used to receive video frames sent by the video processing module 1722 and process the video frames.

[0255] The forgery analysis module 1730 is used to perform forgery analysis on the processed video frames and output forgery analysis information.

[0256] Display frame 1721 can also be used to display fake analysis information to users.

[0257] For example, taking webpage image browsing and chat image browsing scenarios as examples, Figure 18This illustration shows a system architecture diagram for image forgery analysis provided in an embodiment of this application.

[0258] like Figure 18 As shown, the system architecture includes news applications and social applications, as well as an image detection trigger 1810 and a forgery analysis module 1820. The image detection trigger 1810 includes a triggering frame 1811 and an image acquisition module 1812, specifically:

[0259] Triggering Framework 1811 is used to enable users to trigger actions on web page images while browsing news applications, and also to enable users to trigger actions on chat and other images while using social applications.

[0260] The image acquisition module 1812 is used to acquire web page images based on the user's triggering operation on web page images during browsing news applications; it is also used to acquire chat and other images based on the user's triggering operation on chat and other images during using social applications.

[0261] The forgery analysis module 1820 is used to perform forgery analysis on web page images acquired by the image acquisition module 1812; it is also used to perform forgery analysis on chat and other images acquired by the image acquisition module 1812.

[0262] In this embodiment, during the user's browsing of news or social chat, the displayed image can be analyzed for forgery based on the user's triggered operation and the user can be promptly alerted. This can effectively identify forged images and promptly alert the user, reducing the probability of criminals succeeding in using AI technology to commit online fraud. It can also effectively curb the spread of online public opinion, thereby improving the security of users' Internet use.

[0263] One or more modules or units described herein can be implemented in software, hardware, or a combination of both. When any of the above modules or units are implemented in software, the software exists as computer program instructions and is stored in memory. A processor can be used to execute the program instructions and implement the above method flow. The processor can include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., and various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor can be built into a SoC (System-on-a-Chip) or an application-specific integrated circuit (ASIC), or it can be a separate semiconductor chip. In addition to the cores within the processor for executing software instructions to perform calculations or processing, it may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0264] When the modules or units described herein are implemented in hardware, the hardware may be any one or any combination of a CPU, microprocessor, DSP, MCU, artificial intelligence processor, ASIC, SoC, FPGA, PLD, application-specific digital circuit, hardware accelerator, or non-integrated discrete device, which may run the necessary software or perform the above method flow independently of software.

[0265] When the modules or units described herein are implemented using software, they can be implemented, in whole or in part, in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0266] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0267] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0268] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0269] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0270] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0271] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0272] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for identifying forged images, characterized in that, The method includes: When the first image is displayed on the screen of the electronic device, the electronic device performs a forgery analysis on the first image; When the electronic device identifies that there is a fake object in one or more objects in the first image and / or that the scene of the first image is a fake scene and / or that there is a fake element in one or more elements output in association with the first image, the electronic device issues a first reminder to the user. The first reminder is used to mark the fake objects and / or fake scenes and / or fake elements present in the first image.

2. The method according to claim 1, characterized in that, When the first image is displayed on the screen of the electronic device, the electronic device performs forgery analysis on the first image, including: When the first image is displayed on the screen of the electronic device, the electronic device issues a second reminder to the user, the second reminder being used to remind the user whether to perform forgery analysis on the first image; The electronic device performs forgery analysis on the first image based on user confirmation.

3. The method according to claim 1, characterized in that, When the first image is displayed on the screen of the electronic device, the electronic device performs forgery analysis on the first image, including: When the first image is displayed on the screen of the electronic device, the electronic device performs forgery analysis on the first image based on the user's first operation on the first image.

4. The method according to claim 3, characterized in that, The first operation includes: The user drags the first image to the interactive area of ​​the electronic device, or the user selects the first image on the display screen of the electronic device, or the user performs a touch operation on the first control. The first control and the first image are displayed on the same interface, and the first control is used to trigger the electronic device to recognize the first image. The user inputs a first instruction into the electronic device, the first instruction being used to instruct the forgery analysis of the first image.

5. The method according to claim 4, characterized in that, The first operation specifically includes: The user drags the first image to the voice interaction area of ​​the electronic device; The user issues a first voice command to the electronic device, which instructs the user to perform forgery analysis on the first image.

6. The method according to claim 4, characterized in that, The first operation specifically includes: The user selects the first image on the display screen of the electronic device; The user issues a first voice command to the electronic device, which instructs the user to perform forgery analysis on the first image.

7. The method according to claim 4, characterized in that, The first operation specifically includes: The user performs a touch operation on the first control; The user issues a first voice command to the electronic device, which instructs the electronic device to perform forgery analysis on the first image based on the recognition result.

8. The method according to claim 3, characterized in that, When the first image is detected to be displayed on the screen of the electronic device, the electronic device displays a second control on the screen, the first operation including: The user clicks the second control.

9. The method according to claim 8, characterized in that, The second control includes a live window or a card.

10. The method according to any one of claims 1 to 9, characterized in that, The electronic device performs forgery analysis on the first image, including: The electronic device performs forgery analysis on the first image based on the associated information corresponding to the first image. The associated information of the first image includes the sound information and / or geographical location information associated with the first image.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: When the electronic device sends the first reminder to the user, it provides the user with an interception entry and / or a reporting entry, wherein the interception entry is used to trigger an interception mechanism for the first image, and the reporting entry is used to trigger a report that the first image is a fake image.

12. The method according to any one of claims 1 to 11, characterized in that, The first image includes pictures and / or videos.

13. The method according to any one of claims 1 to 12, characterized in that, The first image includes one or more of the following types of images: The video call displayed by the electronic device while running a video call application; The live video displayed by the electronic device while running the live video application; The electronic device displays videos and / or images while running social applications; The electronic device displays videos and / or images while running a browser application; The electronic device displays videos and / or images while running the news application; The electronic device displays videos and / or images while running the gallery application.

14. The method according to any one of claims 1 to 13, characterized in that, The objects in the first image include one or more of people, animals, and objects.

15. An electronic device, characterized in that, include: One or more processors; One or more memory units; And one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, the one or more computer programs including instructions that, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 14.

16. A computer-readable storage medium, characterized in that, The storage medium stores a program or instructions that, when executed, implement the method as described in any one of claims 1 to 14.

17. A chip, characterized in that, The chip stores instructions that, when executed, implement the method as described in any one of claims 1 to 14.

18. A computer program product, characterized in that, The computer program product stores a program or instructions that, when executed, implement the method as described in any one of claims 1 to 14.

Images