Method, apparatus, medium, equipment and procedure for reliability verification of desensitization method

Abstract

Disclosed are a method, apparatus, storage medium, device, and computer program for verifying the reliability of a desensitization method. The method comprises: performing desensitization processing on a first original image using a preset desensitization method to obtain a first desensitized image; performing image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; estimating a first probability value that the first image is a true image; and determining evaluation information based on the first probability value, the evaluation information being used to evaluate the reliability of the preset desensitization method. This method implements an evaluation of the reliability of the image data desensitization method.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a method, device, storage medium, electronic device, and computer program for verifying the reliability of a desensitization method. Background Art

[0002] In practice, images containing sensitive information need to be desensitized to prevent leakage of sensitive information. Usually, the location of the sensitive information in the image is desensitized (for example, by coding) to obtain a desensitized image.

[0003] Desensitized images can be restored through reverse desensitization techniques (e.g., image restoration or restoration) to retrieve sensitive information from the original image. Different data desensitization methods produce desensitized images that perform differently when facing reverse desensitization techniques, indicating that different data desensitization methods have varying reliability.

[0004] There is no method in the related art to verify the reliability of the image data desensitization method. Summary of the Invention

[0005] In order to solve the above technical problems, the present disclosure is proposed. Embodiments of the present disclosure provide a method, apparatus, storage medium, electronic device, and computer program for verifying the reliability of a desensitization method.

[0006] According to one aspect of an embodiment of the present disclosure, a method for verifying the reliability of a desensitization method is provided, including: performing desensitization processing on a first original image by a preset desensitization method to obtain a first desensitized image; performing image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; estimating a first probability value that the first image is a real image; and determining evaluation information based on the first probability value, wherein the evaluation information is used to evaluate the reliability of the preset desensitization method.

[0007] According to another aspect of an embodiment of the present disclosure, a device for verifying the reliability of a desensitization method is provided, including: an image desensitization unit, configured to perform desensitization processing on a first original image through a preset desensitization method to obtain a first desensitized image; an image restoration module, configured to perform image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; a probability prediction unit, configured to estimate a first probability value that the first image is a real image; and an information generation unit, configured to determine evaluation information based on the first probability value, wherein the evaluation information is used to evaluate the reliability of the preset desensitization method.

[0008] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program for executing the reliability verification of the desensitization method in the above embodiments.

[0009] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, which includes: a processor; a memory for storing processor-executable instructions; and a processor for executing a method for verifying the reliability of the desensitization method in the above embodiment.

[0010] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, a method for verifying the reliability of the desensitization method in the above-mentioned embodiment is implemented.

[0011] Based on the above-mentioned embodiments of the present disclosure, a method, apparatus, storage medium, and electronic device for verifying the reliability of a desensitization method are provided. A first original image is desensitized using a preset desensitization method to obtain a first desensitized image. The first desensitized image is then restored to obtain a restored first image. A first probability value that the first image is a true image is estimated. Evaluation information is then generated based on the first probability value. The evaluation information is used to evaluate the reliability of the preset desensitization method. This implements an evaluation of the reliability of the image data desensitization method.

[0012] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0014] Figure 1 is a schematic diagram of a scenario to which the present disclosure is applicable;

[0015] Figure 2 A flowchart of an embodiment of a method for verifying the reliability of the desensitization method disclosed herein;

[0016] Figure 3 A flowchart for generating a first desensitized image in one embodiment of a method for verifying the reliability of the desensitization method disclosed herein;

[0017] Figure 4 A flowchart of generating a first desensitized image in another embodiment of a method for verifying the reliability of the desensitization method disclosed herein;

[0018] Figure 5A flowchart of another embodiment of a method for verifying the reliability of the desensitization method disclosed herein;

[0019] Figure 6 A flowchart for generating evaluation information in one embodiment of a method for reliability verification of a desensitization method disclosed herein;

[0020] Figure 7 A schematic structural diagram of an embodiment of a device for verifying the reliability of the desensitization method disclosed herein;

[0021] Figure 8 A schematic structural diagram of a probability prediction unit in one embodiment of an apparatus for verifying the reliability of the desensitization method disclosed herein;

[0022] Figure 9 A schematic structural diagram of an image desensitization unit in one embodiment of a device for verifying the reliability of the desensitization method disclosed herein;

[0023] Figure 10 A schematic structural diagram of an image desensitization unit in another embodiment of the apparatus for verifying the reliability of the desensitization method disclosed herein;

[0024] Figure 11 A schematic structural diagram of an information generating unit in one embodiment of a device for verifying the reliability of the desensitization method disclosed herein;

[0025] Figure 12 A schematic structural diagram of an information generation module in one embodiment of an apparatus for verifying the reliability of a desensitization method disclosed herein;

[0026] Figure 13 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0027] The exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0028] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0029] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, and do not represent any specific technical meanings, nor do they indicate a necessary logical order between them.

[0030] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0031] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0032] In addition, the term "and / or" in this disclosure merely describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this disclosure generally indicates that the related objects are in an "or" relationship.

[0033] It should also be understood that the description of the various embodiments in this disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0034] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0035] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0036] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0037] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0038] Embodiments of the present disclosure may be applied to electronic devices such as terminal devices, computer systems, and servers, and may operate in conjunction with numerous other general-purpose or specialized computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, or servers include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems.

[0039] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks can be performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media, including storage devices.

[0040] Exemplary Overview

[0041] The present disclosure can use the preset desensitization method to be evaluated to perform desensitization processing on the original image to obtain a desensitized image; then restore the desensitized image to obtain a first image corresponding to the desensitized image; then estimate the first probability value of the first image being a real image, and determine the evaluation information of the preset desensitization method based on the first probability value, and the evaluation information is used to evaluate the reliability of the preset desensitization method. Figure 1 The reliability verification method of the desensitization method disclosed in the present invention is exemplified. Figure 1 A scenario of a method for verifying the reliability of the desensitization method disclosed in the present invention is shown.

[0042] exist Figure 1 In the scenario shown, the electronic device 100 is the executor of the reliability verification method of the desensitization method disclosed in the present invention. The electronic device 100 may be, for example, a terminal computer or a server, on which are loaded the computer software or code corresponding to the preset desensitization method to be evaluated and the computer software or code corresponding to the image restoration algorithm. The executor may desensitize the first original image 110 using the preset desensitization method, for example, the area where the sensitive information in the image is located may be coded to obtain a first desensitized image 120; thereafter, the first desensitized image 120 is restored using a preset image restoration algorithm, for example, a deep neural network for image generation, to obtain a first image 130 corresponding to the first desensitized image 120. Then, a first probability value 140 is estimated to be that the first image 130 is a real image, for example, the first image 130 may be input into a pre-trained machine learning model or deep network model for image recognition. Finally, evaluation information 150 is generated based on the first probability value 140. The evaluation information 150 can represent the reliability of the preset desensitization method. For example, the higher the value of the first probability value 140, the closer the first image 130 is to the first original image 110, which means that the desensitized image obtained by the preset desensitization method can be restored through image restoration to obtain sensitive information. The lower the reliability of the preset desensitization method.

[0043] Exemplary Methods

[0044] Figure 2 Flowchart of one embodiment of the method for verifying the reliability of the desensitization method disclosed in the present invention. Figure 2 As shown, the method includes the following steps:

[0045] Step 200: Desensitize the first original image using a preset desensitization method to obtain a first desensitized image.

[0046] In this embodiment, the preset desensitization method represents the desensitization method to be evaluated. The first original image represents an image that has not been desensitized, for example, it can be a native image (raw format image data) directly output by a camera sensor, or it can be an RGB image obtained by preprocessing (such as color interpolation) the above-mentioned native image. The first desensitized image represents an image obtained after desensitizing the area where the sensitive information in the first original image is located by the preset desensitization method.

[0047] Step 210: Perform image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image.

[0048] In this embodiment, the first image represents an image obtained after image restoration processing is performed on the first desensitized image. The image restoration method may include one or more image anti-desensitization processing algorithms, the purpose of which is to reproduce the sensitive information of a specific area (such as the first target area or the second target area) in the first desensitized image.

[0049] In an optional example, the executing entity may input the first desensitized image obtained in step 200 into a generator in a pre-trained conditional adversarial generative network. The first desensitized image is used as a conditional label, the image data distribution pattern in the first desensitized image is learned, and then the sensitive information in the first desensitized image is simulated according to the distribution pattern using random noise to obtain the first image.

[0050] Step 220: Estimate a first probability value that the first image is a real image.

[0051] In this embodiment, the real image represents the first original image that has not been desensitized. The first probability value represents the degree of similarity between the first image and the first original image. A larger first probability value indicates a greater similarity between the first image and the first original image, and the sensitive information restored from the first image is closer to the actual sensitive information in the first original image.

[0052] As an example, an execution entity may estimate a first probability value that a first image is a real image using an image recognition model. Specifically, the following steps may be included: first, extracting features from the first image relevant to image restoration processing, such as the number, location, and pixel values of pixels with abnormal pixel values; and then estimating the first probability value based on the extracted features.

[0053] In some optional implementations of this embodiment, the execution entity can restore the first desensitized image through multiple image restoration algorithms to obtain first images, and then estimate the probability value of each first image being a real image, and determine the mean or weighted average of the multiple probability values as the first probability value.

[0054] Step 230: Determine evaluation information based on the first probability value.

[0055] In this embodiment, the evaluation information is used to evaluate the reliability of the preset desensitization method and can be presented in the form of text description, numerical value or image data.

[0056] As an example, the execution entity may pre-establish a correspondence between the numerical interval of the first probability value and the evaluation level. For example, when the first probability value is in [0.8, 1.0], it indicates that the first image and the first original image are extremely similar, indicating that the reliability of the preset desensitization method is extremely poor. In this case, the evaluation level corresponding to the interval may be determined as "extremely poor". When the first probability value is in [0, 0.3], it indicates that the first image and the original image are extremely low in similarity, indicating that the reliability of the preset desensitization method is extremely high. In this case, the evaluation level corresponding to the interval may be determined as "excellent". Afterwards, the execution entity may determine the corresponding evaluation level based on the interval of the first probability value obtained in step 220, and obtain the evaluation information of the preset desensitization method.

[0057] For another example, different colors can be set for different numerical ranges to represent the reliability of the preset desensitization method by color.

[0058] This embodiment provides a method for verifying the reliability of a desensitization method. Desensitization is performed on a first original image using a preset desensitization method to obtain a first desensitized image. The first desensitized image is then restored to obtain a restored first image. A first probability value is estimated that the first image is a true image. Evaluation information is then generated based on the first probability value. The evaluation information is used to evaluate the reliability of the preset desensitization method. This method implements a reliability evaluation of the image data desensitization method.

[0059] In some optional implementations of this embodiment, the method can also obtain the first image in the following manner: input the first desensitized image into a generator in a pre-trained adversarial generative network to obtain a first image corresponding to the first desensitized image.

[0060] In this implementation, the generator in the adversarial generative network can be trained to learn the image restoration processing strategy, thereby realizing the restoration processing of the first desensitized image.

[0061] Furthermore, the method can estimate the first probability value in the following manner: input the first image into the discriminator in the adversarial generative network to obtain the confidence of the first image; based on the confidence of the first image, determine the first probability value that the first image is a real image.

[0062] In this implementation, the discriminator in the adversarial generative network can be trained to learn image recognition strategies to determine the probability that the first image output by the generator is a real image.

[0063] In a specific example of this implementation, the adversarial generative network is trained through the following steps: first, constructing a sample set, the sample set including a first sample image labeled 0 and a second sample image labeled 1, the first sample image is an image generated by a pre-constructed generator of an initial adversarial generative network, and the second sample image is an image that has not been desensitized; then, fixing the parameters of the generator, performing initial training on the discriminator, inputting the image in the sample set into the discriminator of the initial adversarial generative network, using the label of the image as the expected output, training the discriminator of the initial adversarial generative network, and obtaining the discriminator after initial training; then, constructing a sample image pair, the sample image pair consisting of a third sample image and its sample label, wherein the sample label is an image that has not been desensitized, and the third sample image is a desensitized image obtained after the sample label is desensitized by data; then, fixing the parameters of the discriminator, performing initial training on the generator, inputting the third sample image in the sample image pair into the generator of the initial adversarial generative network, using the sample label corresponding to the sample image as the expected output, training the generator of the initial adversarial generative network, and obtaining the generator after initial training.

[0064] Afterwards, the generator and discriminator after initial training are connected in series, and the parameters of the generator and discriminator are alternately fixed. The two are alternately iterated until the training termination condition is met, resulting in a trained adversarial generative network. The termination condition can be, for example, a preset number of iterations or the confidence value output by the discriminator. During the alternating iteration process, the parameters of the generator are adjusted based on the results of the discriminator output, so that the generator can generate more realistic images, thereby improving the generator's generation ability; based on the images output by the improved generator, the parameters of the discriminator are adjusted so that the discriminator can recognize images more accurately, thereby improving the discriminator's discrimination ability. Through the adversarial game between the generator and the discriminator, the performance of both is alternately improved.

[0065] In this implementation, the collaborative training and game between the generator and the discriminator in the adversarial generative network can be used to improve the image restoration ability of the generator and the image recognition ability of the discriminator, thereby improving the pertinence and accuracy of the reliability verification method of the desensitization method disclosed in this invention.

[0066] Next reference Figure 3 ,like Figure 3 As shown, in some optional implementations of this embodiment, step 200 may further include the following steps:

[0067] Step 300: Perform demosaicing processing on the first original image to convert the first original image into a three-channel image.

[0068] In this implementation, the first original image may be a native image.

[0069] As an example, the execution entity can input the native image into the ISP (Image Signal Processing), and demosaic the native image through the color restoration module preset in the ISP to obtain a three-channel image corresponding to the native image (for example, it can be an RGB image).

[0070] Step 310: Identify a first target area where sensitive information is located in the three-channel image.

[0071] In this implementation, sensitive information may include privacy information, portrait information, security information, and other types of information. The executing entity may input the three-channel image obtained in step 300 into a pre-trained image recognition model, such as a convolutional neural network model, to identify the first target area where the sensitive information is located from the three-channel image. For example, the outline of the image area where the sensitive information is located may be marked by a detection box.

[0072] Step 320: Adjust the pixel values of the first target area to obtain a first desensitized image.

[0073] As an example, the executing entity can set the pixel value of the first target area to 0 (that is, the values of the three RGB colors are all 0) or other values, so that each pixel in the first target area appears black, thereby hiding the sensitive information and obtaining a first desensitized image.

[0074] In one example, the execution entity may also input the image with the first target area marked into the ISP, and adjust the pixel value of the first target area in the desensitization module in the ISP to obtain a first desensitized image.

[0075] from Figure 3 It can be seen that in Figure 3In the implementation shown, the execution entity can first convert the first original image into a three-channel image, then identify the first target area where the sensitive information is located from the three-channel image, and perform desensitization processing on the first target area to obtain a first desensitized three-channel image.

[0076] Next reference Figure 4 ,like Figure 4 As shown, in some other optional implementations of this embodiment, step 200 may also adopt the following process:

[0077] Step 400: Identify a second target area where sensitive information is located in the first original image.

[0078] In this implementation, the first original image represents a native image that has not been desensitized. As an example, the execution entity may input the native image into a pre-built image recognition model to identify the second target area from the first original image. The image recognition model characterizes the correspondence between the native image and the second target area.

[0079] Step 410: Adjust the pixel values of the second target area to obtain a first desensitized image.

[0080] In this implementation, the executing entity can directly adjust the pixel value of the native image. For example, the brightness value of each pixel in the second target area can be adjusted to the minimum to obtain a first desensitized image, thereby achieving the hiding of sensitive information in the native image.

[0081] from Figure 4 It can be seen that in Figure 4 In the implementation shown, the execution subject can directly identify and desensitize the first original image, and the type of the obtained first desensitized image is a native image.

[0082] Next reference Figure 5 , Figure 5 A flow chart of another embodiment of a method for verifying the reliability of the desensitization method of the present disclosure is shown, Figure 5 As shown, the process includes the following steps:

[0083] Step 500: Desensitize the first original image using a preset desensitization method to obtain a first desensitized image.

[0084] Step 510: Perform image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image.

[0085] Step 520: Estimate a first probability value that the first image is a real image.

[0086] In the embodiment, steps 500 to 520 correspond to the aforementioned steps 200 to 220, respectively, and are not described again here.

[0087] Step 530: Desensitize the at least one second original image using a preset desensitization method to obtain at least one second desensitized image.

[0088] In this embodiment, the at least one second original image is an image different from the first original image. For example, the at least one second original image may include one image or multiple different images.

[0089] Step 540: Perform image restoration processing on at least one second desensitized image to obtain a second image corresponding to each of the at least one desensitized images.

[0090] Step 550: Determine a probability value that the second image corresponding to each of the at least one second desensitized images is a real image, and obtain at least one second probability value.

[0091] In this embodiment, the process of desensitizing, restoring and estimating the first probability value of the first original image corresponds to the process of desensitizing, restoring and estimating the second probability of at least one second original image, which will not be repeated here.

[0092] Step 560: Determine evaluation information based on the first probability value and at least one second probability value.

[0093] As an example, the execution entity may first determine the average of the first probability value and at least one second probability value, and then determine the evaluation level according to the numerical range in which the average lies, to obtain evaluation information of the preset desensitization method.

[0094] from Figure 5 It can be seen that with Figure 2 Compared to the embodiment shown, Figure 5 The illustrated embodiment demonstrates determining evaluation information based on the probability of multiple images obtained from a preset desensitization method being true images. Using multiple images can more accurately characterize the overall performance of the preset desensitization method, thereby improving the accuracy of the reliability verification of the preset desensitization method.

[0095] Next reference Figure 6 ,like Figure 6 As shown, in some optional implementations of this embodiment, step 560 may further include the following steps:

[0096] Step 600: Determine a first weight coefficient of the first desensitized image in determining evaluation information.

[0097] In this implementation, the first weight coefficient represents the importance of the first desensitized image to the evaluation result.

[0098] Step 610: Determine a second weight coefficient for each of at least one second desensitized image in determining evaluation information.

[0099] In this implementation, the second weight coefficient represents the importance of at least one second desensitized image to the evaluation result.

[0100] Step 620: Weight the first probability value and at least one second probability value based on the first weight coefficient and the corresponding second weight coefficient to determine evaluation information.

[0101] As an example, a mapping relationship between the weighted sum or weighted average value and the evaluation level can be pre-constructed, and then the execution entity can determine the weighted sum or weighted average of the first probability value and at least one second probability value, and map the value to the evaluation level to determine the evaluation level of the preset desensitization method and obtain evaluation information.

[0102] In this implementation, the importance of the first desensitized image in the evaluation result is represented by a first weight coefficient, the importance of the second desensitized image in the evaluation result is represented by a second weight coefficient, and the evaluation information of the preset desensitization method is determined based on the weighted result of the first probability value and at least one second probability value, so that the reliability of the preset desensitization method can be evaluated more accurately.

[0103] Exemplary devices

[0104] Figure 7 This is a schematic diagram of the structure of an embodiment of a device for verifying the reliability of the desensitization method disclosed in the present invention. The device of this embodiment can be used to implement the corresponding method embodiment of the present invention. Figure 7 The device shown includes: an image desensitization unit 710, configured to perform desensitization processing on a first original image by a preset desensitization method to obtain a first desensitized image; an image restoration module 720, configured to perform image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; a probability prediction unit 730, configured to estimate a first probability value that the first image is a real image; an information generation unit 740, configured to determine evaluation information based on the first probability value, and the evaluation information is used to evaluate the reliability of the preset desensitization method.

[0105] In this embodiment, the image desensitization unit 710 is further configured to: input the first desensitized image into a generator in a pre-trained adversarial generative network to obtain a first image corresponding to the first desensitized image.

[0106] like Figure 8As shown, in this embodiment, the probability prediction unit 730 further includes: a prediction module 731, configured to input the first image into the discriminator in the adversarial generative network to obtain the confidence of the first image; a determination module 732, configured to determine the probability value of the first image being a real image based on the confidence of the first image.

[0107] like Figure 9 As shown, in this embodiment, the image desensitization unit 710 further includes: an image conversion module 711, configured to perform de-mosaicing on the first original image and convert the first original image into a three-channel image; a first identification module 712, configured to identify a first target area where sensitive information is located in the three-channel image; a first desensitization module 713, configured to adjust the pixel value of the first target area to obtain a first desensitized image.

[0108] like Figure 10 As shown, in this embodiment, the image desensitization unit 710 further includes: a second identification module 714, configured to identify a second target area where sensitive information is located in the first original image; a second desensitization module 715, configured to adjust the pixel value of the second target area to obtain a first desensitized image.

[0109] like Figure 11 As shown, in this embodiment, the information generation unit 740 further includes: a third desensitization module 741, which is configured to determine that at least one second original image is desensitized by a preset desensitization method to obtain at least one second desensitized image, and at least one second original image is an image different from the first original image; an image restoration module 742, which is configured to perform image restoration processing on at least one second desensitized image to obtain a second image corresponding to each of the at least one desensitized images; a probability prediction module 743, which is configured to determine a probability value that the second image corresponding to each of the at least one second desensitized images is a real image, and obtain at least one second probability value; an information generation module 744, which is configured to determine evaluation information based on the first probability value and the at least one second probability value.

[0110] like Figure 12 As shown, in this embodiment, the information generation module 744 further includes: a first weight submodule 7441, configured to determine a first weight coefficient of the first desensitized image in determining the evaluation information; a second weight submodule 7442, configured to determine a second weight coefficient of at least one second desensitized image in determining the evaluation information; a weighting submodule 7443, configured to weight the first probability value and at least one second probability value based on the first weight coefficient and the respective corresponding second weight coefficients to determine the evaluation information.

[0111] Exemplary electronic devices

[0112] Reference below Figure 13 An electronic device according to an embodiment of the present disclosure is described. Figure 13 FIG. 1 shows a block diagram of an electronic device according to an embodiment of the present disclosure. Figure 13 As shown, electronic device 1300 includes one or more processors 1310 and memory 1320 .

[0113] The processor 1310 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 1300 to perform desired functions.

[0114] The memory 1320 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, may include: random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory, for example, may include: read-only memory (ROM), hard disk, and flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement functions such as the method for reliability verification of the desensitization method of each embodiment of the present disclosure described above. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0115] In one example, the electronic device 1300 may further include an input device 1330 and an output device 1340, etc. These components are interconnected via a bus system and / or other forms of connection mechanisms (not shown). In addition, the input device 1330 may also include, for example, a keyboard, a mouse, etc. The output device 1340 may output various information to the outside. The output device 1340 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0116] Of course, to simplify, Figure 13 Only some of the components related to the present disclosure in the electronic device 1300 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 1300 may further include any other appropriate components.

[0117] Exemplary computer program products and computer-readable storage media

[0118] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the method for reliability verification of the desensitization method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0119] The computer program product may be written in any combination of one or more programming languages to implement the operations of the disclosed embodiments, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0120] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps of the method for training a language model according to various embodiments of the present disclosure or the method for predicting the probability of occurrence of a word based on a language model described in the above “Exemplary Method” section of this specification.

[0121] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive enumeration) of readable storage media can include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0122] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of the present disclosure. In addition, the specific details disclosed above are merely illustrative and comprehensible, and are not restrictive. The above details do not limit the present disclosure to necessarily being implemented using the above specific details.

[0123] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0124] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are intended to be illustrative examples only and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words that mean "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to," and can be used interchangeably therewith.

[0125] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0126] It should also be noted that in the apparatus, device, and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0127] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0128] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for verifying the reliability of a desensitization method, comprising: Performing desensitization processing on the first original image by a preset desensitization method to obtain a first desensitized image; Performing image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; Estimating a first probability value that the first image is a real image, comprising: inputting the first image into a discriminator in a pre-trained adversarial generative network to obtain a confidence level of the first image; and determining a first probability value that the first image is a real image based on the confidence level of the first image; wherein the real image is the first original image, and the first probability value represents a degree of similarity between the first image and the first original image; and the first probability value is used to represent a probability of obtaining sensitive information from the first desensitized image through image restoration; Based on the first probability value, evaluation information is determined, where the evaluation information is used to evaluate the reliability of the preset desensitization method.

2. The method according to claim 1, wherein Performing image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image includes: The first desensitized image is input into the generator in the adversarial generative network to obtain a first image corresponding to the first desensitized image.

3. The method according to claim 1, wherein Performing desensitization processing on the first original image by a preset desensitization method to obtain a first desensitized image includes: Performing demosaicing on the first original image to convert the first original image into a three-channel image; Identifying a first target area in the three-channel image where sensitive information is located; The pixel values of the first target area are adjusted to obtain the first desensitized image.

4. The method according to claim 1, wherein Performing desensitization processing on the first original image by a preset desensitization method to obtain a first desensitized image includes: Identifying a second target area in the first original image where sensitive information is located; The pixel values of the second target area are adjusted to obtain the first desensitized image.

5. The method according to any one of claims 1 to 4, wherein: The determining of evaluation information based on the first probability value includes: Desensitizing at least one second original image using the preset desensitization method to obtain at least one second desensitized image, wherein the at least one second original image is an image different from the first original image; Performing image restoration processing on the at least one second desensitized image to obtain a second image corresponding to each of the at least one desensitized images; Determining a probability value that the second image corresponding to each of the at least one second desensitized images is a real image, to obtain at least one second probability value; The evaluation information is determined based on the first probability value and the at least one second probability value.

6. The method according to claim 5, wherein: Determining evaluation information based on the first probability value and the at least one second probability value includes: determining a first weight coefficient of the first desensitized image in determining the evaluation information; determining a second weight coefficient for each of the at least one second desensitized image in determining the evaluation information; The first probability value and the at least one second probability value are weighted based on the first weight coefficient and the respective corresponding second weight coefficient to determine evaluation information.

7. A device for verifying the reliability of a desensitization method, comprising: An image desensitization unit is configured to perform desensitization processing on the first original image using a preset desensitization method to obtain a first desensitized image; an image restoration module configured to perform image restoration processing on the first desensitized image to obtain a first image corresponding to the first desensitized image; a probability prediction unit configured to estimate a first probability value that the first image is a real image, specifically configured to: input the first image into a discriminator in a pre-trained adversarial generative network to obtain a confidence level of the first image; and determine a first probability value that the first image is a real image based on the confidence level of the first image; wherein the real image is the first original image, and the first probability value represents a degree of similarity between the first image and the first original image; The information generating unit is configured to determine evaluation information based on the first probability value, where the evaluation information is used to evaluate the reliability of the preset desensitization method.

8. A computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 6.

9. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images