CREATING AN ASSESSMENT MASK FOR MULTI-FACTOR AUTHORIZATION VERIFICATION

Abstract

A computer-implemented method for multi-factor authentication, wherein the computer-implemented method comprises: generating a scoring mask (206) over one or more modified elements on a modified image, the modified image being generated by a generative adverse network (GAN); creating a scoring grid by comparing an original image with the modified image to detect mismatched pixels between the original image and the modified image; overlaying the scoring mask over the detected mismatched pixels on the modified image; displaying the modified image (208) as a multi-factor authentication prompt to a user, the user being prompted to provide a response that identifies one or more modifications in the modified image;Calculating an assessment score (214) by comparing the user's response with the assessment mask to validate the user's response; and in response to reaching or exceeding a predetermined threshold, checking the user's authorization and granting user access to data or other resources.

Description

BACKGROUND OF THE INVENTIONThe present invention relates generally to the field of multi-factor authentication, and more particularly to creating media files as a means for multi-factor authentication.A generative adventitious network (GAN) is a machine learning (ML) model in which two neural networks compete with one another to make more accurate predictions. GANs typically run unsupervised and use a cooperative zero sum game for learning. The two neural networks that make up a GAN are referred to as a generator and discriminator. The generator is a convolutional neural network and the discriminator is a deconvolution neural network. The purpose of the generator is to generate artificial outputs which can be easily confused with real data. The object of the discriminator is to identify which of the outputs it has produced artificially. Basically, GANs generate their own training data. As the feedback loop continues between opposing networks, the generator produces more and more quality results and the discriminator becomes increasingly better to detect artificially generated data.The first step in establishing a GAN is to determine the desired final output and collect a first training data set based on these parameters. These data are then randomized and input to the generator as an input until the generator has achieved a basic accuracy in generating outputs. Subsequently, the generated images are input to the discriminator together with the actual data points of the original concept. The discriminator filters the information and returns a probability between 0 and 1 for each image to map the authenticity of the image (1 stands for true and 0 stands for false). These values are then checked manually for success and repeated until the desired result is achieved. The core idea of a GAN is based on the "indirect" training by the discriminator, which is also dynamically updated. This essentially means that the generator is not trained to minimize the distance to a particular image, but rather to deceive the discriminator. This allows the model to learn unsupervised. GANs develop into a popular ML model for online retailing because they are able to understand and accurately render visual content.US 2018 / 0101674 A1 describes methods and systems for electronic authentication. US 2014 / 0 282 959 A1 describes a system and a method for computer authentication with user modification of an image using a shared secret.SUMMARYThe invention is described by the features of the independent claims. Embodiments are set out in the dependent claims.Embodiments of the present invention disclose a method, computer program product, and system for multi-factor authentication, the computer-implemented method comprising: generating an evaluation mask over one or more modified elements on a modified image, the modified image being generated by a generative advanced network (GAN); generating an evaluation grid by comparing an original image with the modified image to detect different pixels between the original image and the modified image; overlaying the evaluation mask over the detected different pixels on the modified image; displaying the modified image as a multi-factor authentication prompt to a user, prompting the user to provide a response that detects one or more modifications in the modified image; calculating a score based on a comparison of the user's response with the score mask to validate the user's response; and responsive to the score reaching or exceeding a predetermined threshold, checking the user for authorisation and granting user access to data or other resources.BRIEF DESCRIPTION OF THE DRAWINGSFIG. 1 is a functional block diagram illustrating a distributed computing environment according to an embodiment of the present invention; FIG. 2 illustrates the functional steps of a server computer authentication mechanism 122 in the distributed computing environment of FIG. 1 for multi-factor authentication, in accordance with an embodiment of the present invention; and FIG. 3 is a block diagram of the components of the server computer executing the authentication mechanism in the distributed computing environment of FIG. 1, in accordance with an embodiment of the present invention.DETAILED DESCRIPTIONEmbodiments of the present invention improve upon the prior art in the field of online account security by executing a second authentication factor. In particular, embodiments of the present invention improve upon the prior art by creating an evaluation mask (i.e., a mask) over modified elements in a media file created by a GAN, thus effecting a multi-factor authentication. Embodiments of the present invention may rely on media files known to the user (e.g., a personal media file) and test the user's prior knowledge of the original media file. A personal media file may be a family photograph, an image of the first car or house of the user, and / or any personalized image or video known in the art. Embodiments of the present invention improve the current state of the art of user authentication in that they do not require user personal data such as birth date, age or address, but instead use knowledge of a media file as a parameter for user authentication. Embodiments of the present invention compare an original media file to the modified media file to determine differences based on pixel changes. By comparing differences between pixels, embodiments of the present invention can recognize such differences as "target areas" to superimpose a mask on them and use them as validation points in a media file. Embodiments of the present invention generate a scoremask of modified elements in a media file created by a GAN as a means for multi-factor authentication. Embodiments of the present invention improve upon the prior art by creating authentication tasks to be solved using GAN as a new form of multi-factor authentication applicable to digital experiences and on screen-resting devices (e.g., computing devices).Embodiments of the present invention create a score grid by comparing an original image to a GAN modified version of the image (i.e., a modified image) to detect variant pixels between the original image and the modified image and placing a mask over the detected variant regions. Embodiments of the present invention refer to the detected deviating regions as "deviating regions". After the modified image is presented to the user, embodiments of the present invention receive the user's response in the form of touching, drawing, or clicking via a user interface, where the received user responses (i.e., the input information) are compared to the mask (from pixel areas to pixel areas) to process / validate the user's inputs. Embodiments of the present invention review the user's prior knowledge of the original media file and validate the user's response by comparing the original media file to the detected deviating regions in the user's response to the modified media file, the user's response then being validated if the user's response) is within a predetermined acceptable limit. For example, embodiments of the present invention validate a user when the user's response selects / recognizes 98% of the differing areas in the modified image.The implementation of embodiments of the invention may be performed in various ways, wherein details of exemplary implementations are discussed below with reference to the figures (i.e., FIGS. 1 to 3 ).FIG. 1 is a functional block diagram illustrating a distributed computing environment, generally designated 100, in accordance with an embodiment of the present invention. As used in this specification, the term "distributed" refers to a computer system that includes multiple, physically separate units that together operate as a single computer system. FIG. 1 merely illustrates an embodiment and is not to be considered limiting to environments in which other embodiments may also be implemented. Those skilled in the art can make numerous changes to the environment set forth in the claims without departing from the scope of the invention as described in the claims. The distributed computing environment 100 includes a computing device 110 and a server computer 120 interconnected via a network 130.The network 130 may be, for example, a storage network (SAN), a telecommunications network, a local area network (LAN), a wide area network (WAN) such as the Internet, a wireless technology for short-range data exchange (using short-wavelength ultra-high frequency (UHF) radio waves in the ISM band of 2.4 to 2.485 GHz from fixed and mobile units and the establishment of personal area networks (PANs), or a combination of these three technologies), and may include wired, wireless, or fiber optic links. The network 130 may include one or more wired and / or wireless networks that may receive and transmit data, voice, and / or video signals, including multimedia signals including voice, data, text, and / or video data. In general, network 130 may be any combination of connections and protocols that support communication between computing device 110 and server computer 120, as well as other computing devices and / or storage devices (not shown in FIG. 1 ) in distributed computing environment 100.In some embodiments of the present invention, computing device 110 may be a stand-alone device, a client, a server, a laptop computer, a tablet computer, a netbook computer, a personal computer (PC), a smartphone, a desktop computer, a smart TV, a smart watch, a radio, a stereo, a cloud-based service (e.g., a cognitive cloud resting service), AR glasses, a virtual reality headset, any HUD known in the art, and / or any programmable electronic computing device capable of:, The system may provide communication over the network 130, or any combination thereof, with various components and devices in the distributed computing environment 100. In general, computing device 110 may be any programmable computing device or combination of programmable computing devices capable of executing machine-readable program instructions and communicating with users of other computing devices over network 130, and / or capable of executing machine-readable program instructions and communicating with server computer 120. In some embodiments, computing device 110 may include a plurality of computing devices.In some embodiments of the present invention, computing device 110 may be any programmable electronic computing device or combination of programmable electronic computing devices capable of executing machine readable program instructions, manipulating executable machine readable instructions, and communicating over a network, such as network 130, with server computer 120 and other computing devices (not shown) in distributed computing environment 100. The computing device 110 may include an instance of a user interface (interface) 106 and local memory 104. In various embodiments not shown in FIG. 1, the data processing unit 110 may include a plurality of interfaces 106. In other embodiments, not shown in FIG. 1, the distributed computing environment 100 may include a plurality of computing devices, a plurality of server computers, and / or a plurality of networks. The computing device 110 may include internal and external hardware components, as illustrated and described in more detail with respect to FIG. 3.The user interface (interface) 106 provides an interface to the automatic authentication feedback and mechanism 122. With the computing device 110, a user and / or a client may interact with the authentication mechanism 122 and / or the server computer 120 via the user interface 106 in various ways, such as by sending program instructions, receiving program instructions, sending and / or receiving messages, updating data, sending data, inputting data, editing data, collecting data, and / or receiving data. In one embodiment, the interface 106 may be a graphical user interface (GUI) or a web user interface (WUI), and may display at least text, documents, web browser windows, user options, application interfaces, and operating instructions. The interface 106 may include data (such as graphics, text, and sound) presented to a user, as well as control sequences that the user employs to control functions. In another embodiment, the interface 106 may be mobile application software that interfaces between a user of the computing device 110 and the server computer 120. The mobile application software, or an "app", may be designed to run on smart phones, tablet computers, and other computing devices. In one embodiment, the user of the computing device may at least send data, enter data, edit data (annotations), collect data, and / or receive data via the interface 106.The server computer 120 may be a stand-alone computing device, a management server, a web server, a mobile computing device, one or more client servers, or another electronic device or computer system capable of receiving, transmitting, and processing data. In other embodiments, server computer 120 may be a server computer system that uses multiple computers such as, but not limited to, a server system, such as in a cloud computing environment. In another embodiment, server computer 120 may be a computer system that uses clustered computers and components (e.g., database servers, application servers, and so forth) that function as a single pool of seamless resources when accessed in distributed computing environment 100. The server computer 120 may include internal and external hardware components, as illustrated and described in more detail with respect to FIG. 3. In some embodiments, the server computer 120 may be formed of a plurality of server computers.Each of the shared memory 124 and the local memory 104 may be a data / knowledge storage and / or database that may be written and / or read by one or a combination of the authentication mechanism 122, server computer 120, and computing device 110. In the illustrated embodiment, shared memory 124 is located on server computer 120 and local memory 104 is located on computing device 110. In another embodiment, shared memory 124 and / or local memory 104 may be present elsewhere in distributed computing environment 100, provided that both may access and be accessible to computing device 110 and server computer 120. Both the shared memory 124 and the local memory 104 may be implemented with any type of storage device capable of storing data and configuration files that the server computer 120 can access and use, such as, but not limited to, a database server, a hard disk drive, or flash memory.In the illustrated embodiment, authentication mechanism 122 is executed on server computer 120. In other embodiments, authentication mechanism 122 may be executed on computing device 110. In various embodiments of the present invention not shown in FIG. 1, authentication mechanism 122 may be executed on a plurality of server computers 120 and / or on a plurality of data processing units 110. In some embodiments, authentication mechanism 122 may be located and / or executed anywhere in distributed computing environment 100 as long as authentication mechanism 122 is connected to and / or exchanges data with computing device 110 and / or server computer 120 via network 130.In various embodiments of the present invention, authentication mechanism 122 is a multi-factor authentication mechanism. The authentication mechanism 122 may include and execute a GAN model. In the illustrated embodiment, authentication mechanism 122 includes capture component 125, security image scoring mask module (scoring module) 126, and rendering component 128. In other embodiments, the sensing component 125, the scoring module 126, and / or the rendering component 128 may each be executed on the computing device 110. In various embodiments of the present invention not shown in FIG. 1, the acquisition component 125, the evaluation module 126 and / or the presentation component 128 can each be executed on a plurality of server computers 120 and / or on a plurality of data processing units 110. In some embodiments, the capture component 125, the evaluation module 126, and / or the presentation component 128 may be located and / or executed anywhere in the distributed computing environment 100, as long as the capture component 125, the evaluation module 126, and / or the presentation component 128 are connected to and / or communicate with the authentication mechanism 122, the computing device 110, and / or the server computer 120 via the network 130.The authentication mechanism 122 may receive uploaded media files (e.g., digital photos (i.e., photos / images)) and metadata from a user or database (i.e., local storage 104 and / or shared storage 124) via the capture component 125. In some embodiments of the present invention, the received media files (e.g., user photos) may be photos associated with the personal nature and / or the user. The media files and metadata may be obtained from one or more social media pages and / or open source web pages on the Internet, and the GAN model authentication mechanism 122 may use the obtained media files to generate modified media files. In other embodiments, the authentication component uses other available images of a predetermined location via a GAN model to generate modified media files. Metadata may include: location of the photograph, name of the location, time of year, time stamp of the photograph, file size, number of pixels, and / or any descriptive, structural, and administrative metadata known in the art. The media files may be photographs, videos, and / or any type of media files known in the art. In various embodiments of the present invention, the received and / or retrieved metadata is associated with a particular media file. In some embodiments of the present invention, authentication mechanism 122 is associated or synchronized with one or more social media profiles of a user.The authentication mechanism 122 may have user enabled access to search for data or other resources, such as photos and metadata from the associated one or more social media profiles of the user. For example, the authentication mechanism 122 retrieves the user's current social media profile image and creates a modified image that is presented to the user for authentication, prompting the user to recognize / select the differences in the modified image. In various embodiments of the present invention, authentication mechanism 122 performs an Internet search via one or more search engines to find media files (e.g., photos) and metadata. In various embodiments of the present invention, authentication mechanism 122 receives media files directly from the user.Authentication mechanism 122 may generate, via evaluation module 126, a modified / modified media file based on an original or uploaded image / photograph. In various embodiments of the present invention, the evaluation module 126 performs two steps: (i) changing the original image (e.g., a uploaded user media file) using the GAN model, and (ii) creating and placing a mask over the modified media file to evaluate the user's response (i.e., the response), the mask including information about where the changes were made to the original media file, the mask not visible to the user checking for authorisation. In various embodiments of the present invention, the authentication mechanism 122 makes changes to the persons, mode, age, color, and pixels in the user uploaded image via the evaluation module 126, generates a modified second image based on the uploaded image, compares the two images, and creates and places a mask over the areas in the modified second image that were changed from the uploaded image.For example, a user uploads a photograph of a local park, the photograph of the park including pedestrians making dogs, trees, pedestrians walking skates, birds flying through the air, and a pond. In this example, authentication mechanism 122 generates a modified image of the uploaded parking photograph via capture component 125 and a GAN model, the modified image removing the dogs being performed, adding birds to the tree, changing the color of the leaves from green to yellow, adding ducks to the pond, changing the color of the west of one of the pedestrians, and removing the birds flying at the sky, and pitting the area where the birds were removed. In this example, the authentication mechanism 122 generates a mask via the scoring module 126 and superimposes it over the modified image to score the user's responses. In this example, the modified image is displayed to the user and is prompted to recognize the changes in the modified image from the uploaded parking photograph. As the user selects portions of the modified image, the mask, via the scoring module 126, registers the user's responses and uses the obtained user responses to calculate a score.In various embodiments of the present invention, the mask is not visible to the user and is intended to serve as an interactive component that the user can click on via the interface 106. Based on this interaction, the assessment module 126 may determine whether the user has correctly selected one or more changes to the original image to detect / confirm that the user has prior knowledge of the image. In various embodiments of the present invention, authentication mechanism 122 prompts the user to select / recognize a predetermined number of changes in a modified media file. For example, the user is prompted to select at least three changes in the image.In various embodiments of the present invention, the rendering component 128 displays a modified image and one or more open questions via the interface 106. For example, the presentation component 128 displays a modified image and a single open question, such as "identify differences" or "choose changes in image", to a user via the interface 106. In this example, the presentation component 128 prompts the user to click on "OK" to continue. The differences in the modified image may be one or more differences from the original image. The presentation component 128 may record and return the user's interactions to the displayed one or more open questions to a predetermined instance or the scoring module 126, where the scoring module 126 performs the second step (i.e., the security image scoring). The scoring module 126 may then compare the user's response(s) with the scoring mask to calculate a score. In various embodiments of the present invention, in some cases, a plurality of media files (original and / or edited) may be required to more accurately evaluate the user's response(s).The presentation component 128 may evaluate how accurate the response of a user to a task to be solved (i.e., a questioned) was, wherein the accuracy / accuracy of the response of a user is determined based on a predetermined threshold. In various embodiments of the present invention, the predetermined threshold may be defined by the user during setup or at any time via the user settings. In assessing the accuracy of the user response, the rendering component 128 may take into account the order of the selected objects and the time required to provide the response.In various embodiments of the present invention, the authentication mechanism 122 returns the predetermined threshold to the website or mobile application for recognition in a binary format. The user's status is either authenticated or unauthenticated based on the calculated score for the one or more user's responses, wherein the user's status is sent to the website or mobile application with which the user interacts, wherein the website processes the binary result to grant or deny access accordingly.In various embodiments of the present invention, the authentication mechanism 122 compares images and detected differences to create tasks to be accomplished and prevent fraud, where the tasks to be accomplished may be modified media files used to authenticate a user. In various embodiments of the present invention, authentication mechanism 122 adjusts the media file according to the user specified preferences and access setting. For example, the image colors are changed for users with color lack of visibility. The display of the image can be timed so that the time available to the user to detect the differences in the changed data file can be adjusted by increasing or decreasing the time assigned. In some embodiments, the time available to the user to detect the differences in the edited media file is predetermined.In various embodiments of the present invention, authentication mechanism 122 performs eye tracking (eye tracking) via a camera component not shown in FIG. 1 to determine what the user viewed and to relate the user's gaze pattern to his selection. To determine a score, the authentication mechanism 122 detects and analyzes the items / areas of the media file that a user spent viewing and the items / areas that the user selected.FIG. 2 illustrates the functional steps of the authentication mechanism 122, generally designated 200, in communication with the computing device 110 in the distributed computing environment 100 of FIG. 1 for multi-factor authentication, in accordance with an embodiment of the present invention. FIG. 2 provides an illustration of an implementation and is not to be considered as limiting the environments in which various embodiments may be implemented. Those skilled in the art can make numerous changes to the environment illustrated without departing from the scope of the invention as described in the claims.In step 202, the authentication mechanism 122 receives a user's media file. In various embodiments of the present invention, authentication mechanism 122 receives one or more media files from a user or retrieves one or more media files from local memory 104 and / or shared memory 124. For example, a user that is new on a social media website logs an account, requesting the user to upload a security image and to display corresponding metadata such as the season, location, city, and country (e.g., Filids Street Station, summer). In this example, the user uploads an image of a birthday place that he has recently obtained. In various embodiments of the present invention, authentication mechanism 122 prompts the user to upload new / current media after a predetermined period of time (e.g., weeks, months, and so forth).In step 204, the authentication mechanism 122 generates a GAN modified media file. In various embodiments of the present invention, authentication mechanism 122 generates one or more GAN16 media files from the received one or more user media files. Continuing with the above example, a user's account is affected by a security threat (e.g., a hacking attempt). In this example, the authentication mechanism 122 is warned of the security threat and caused to perform multi-factor authentication. In this example, the authentication mechanism 122 retrieves the image originally uploaded by the user (e.g., the user-defined birthday sites) as well as the metadata from the local storage 104 and / or the shared storage 124, and detects similar images of the same site, different angles, objects, people, and lighting from the Internet. In various embodiments of the present invention, the authentication mechanism 122 processes the original image using a GAN-based image variation model, the processes including, but not limited to, changing objects, people, colors, brightness, age of the people, changing walls, changing clothing, and fashion in the original image. For example, changing the color of the sugar cast, changing the name on the pie, changing the books on the shelf in the background in plants, reducing the number of candles, adding a photograph to the wall behind the pie, and changing the brightness of the candles and the room.In step 206, the authentication mechanism 122 generates an assessment mask. In various embodiments of the present invention, authentication mechanism 122 performs a pixel-to-pixel comparison between the original media file and the GAN modified media file (e.g., the modified media file). Based on the pixel comparison, the authentication mechanism 122 may recognize the regions that differ between the original media file and the modified media file, and mark the recognized different regions as "deviations.". Based on the detected "deviations", the authentication mechanism 122 may superimpose one or more masks from the deviations, where the one or more masks are scoring points. In various embodiments of the present invention, the authentication mechanism 122 generates one or more scoring grids from comparing an original image with a GAN-modified version of the image to detect different pixels between the original image and the modified image and place a mask over the detected "deviations.".In step 208, the authentication mechanism 122 displays the modified media file to the user. In various embodiments of the present invention, authentication mechanism 122 displays one or more modified media files with the overlaid mask to the user via interface 106. Continuing with the above example, the authentication mechanism 122 displays the altered image with the evaluation mask (i.e., the mask) to the hacker.In step 210, the authentication mechanism 122 issues a display request to the user in response. In various embodiments of the present invention, the authentication mechanism 122 responsively issues one or more display requests to the user, the display requests being responsively displayed to the user via the interface 106. Continuing with the above example, upon displaying the modified image with the overlaid mask, the authentication mechanism 122 issues a prompt to the hacker (i.e., the user) in response to instructing the hacker to recognize the elements of the image that have changed by either typing, drawing, and / or clicking on the elements, depending on the type of computing device used by the hacker. In various embodiments of the present invention, authentication mechanism 122 uses HoloGAN (i.e., GAN) to enable the conversion of 2D images to 3D by adding depth to the original media file and to allow users to rotate the angle of the media file (e.g., the altered image) to select items that have been placed (e.g., items behind other objects). The selection of the user (i.e. the selection) on the basis of the request as a reaction can also be effected by first selecting the depth level and typing a predetermined object in a selected level of the media file.In step 212, the authentication mechanism 122 compares the received user response information (i.e., user selection) with the assessment mask. To calculate the score, in various embodiments of the present invention, the authentication mechanism 122 compares the user's selection to the scoremask. Continuing with the above example, if the auditor mechanism 122 receives the selection(s) of the hacker, the auditor mechanism 122 compares the received selection(s) to the generated mask to determine whether the hacker has detected the proper areas on the altered image. In various embodiments of the present invention, in some cases, a plurality of media files (original and / or edited) may be required to more accurately evaluate the user.In step 214, the authentication mechanism 122 calculates an assessment score based on the user's response. In various embodiments of the present invention, authentication mechanism 122 calculates an evaluation score from comparing the received user response(s) and the evaluation mask. In some embodiments of the present invention, the authentication mechanism 122 for validating the user's response calculates an evaluation score from comparing the user's response to the evaluation mask. In various embodiments of the present invention, authentication mechanism 122 calculates a score from multiple attempts to identify successful detection, the multiple attempts including a plurality of media files, the plurality of media files being different media files and / or the same media file with different modifications. In various embodiments of the present invention, the authentication mechanism 122 calculates the score based on a plurality of response attempts of the user to validate a detection of the user, the plurality of response attempts being based on a plurality of security requests each using a different modified image selected from a plurality of modified images.In step 216, the authentication mechanism 122 determines whether the user is authenticated. In various embodiments of the present invention, the authentication mechanism 122 determines whether the user is authenticated based on the calculated score. In various embodiments of the present invention, authentication mechanism 122 sends a binary "user-checked" or "user-not-checked" decision to the platform to grant or deny access to data or other resources to the user. If the user's score is within or above a predetermined threshold ("yes" step), the authentication mechanism 122 validates and authenticates the user and proceeds to step 220. If the user score is below the predetermined threshold ("no" step), the authentication mechanism 122 cannot validate the user and proceeds to step 218.In step 218, the authentication mechanism 122 prompts the user to retry authentication. In various embodiments of the present invention, authentication mechanism 122 denys user access to the data or other resources and prompts user to retry authentication, the prompt being a prompt displayed via interface 106 in response. In the illustrated embodiment, the authentication mechanism 122 may repeat steps 204-218 until the user is validated or the predetermined number of attempts is reached and the account is locked.In step 220, the authentication mechanism 122 grants access to the user. In various embodiments of the present invention, the authentication mechanism 122 grants the user access to data or other resources based on the score and authentication, where the score reaches or exceeds a predetermined threshold. In various embodiments of the present invention, authentication mechanism 122 issues a survey to evaluate the difficulty and accuracy of the modified media file and authentication process.FIG. 3 illustrates a block diagram of the components of the server computer 120 in the distributed computing environment 100 of FIG. 1, in accordance with an embodiment of the present invention. It should be appreciated that FIG. 3 provides only one implementation and is not to be considered in a limiting sense of the environments in which various embodiments may be implemented. Numerous changes can be made to the environment depicted.FIG. 3 shows computer system 300, server computer 120 illustrating an example of computer system 300 that includes authentication mechanism 122. The computer system includes processors 301, a cache 303, a memory 302, persistent storage 305, a communication device 307, one or more input / output interfaces 306, a display 309, one or more external device(s) 308, and a communication fabric 304. The communication structure 304 provides communication between the cache 303, the memory 302, the persistent storage 305, the communication unit 307, and the input / output interface(s) 306. The communication fabric 304 may be implemented with any architecture designed for passing data and / or control information between processors (such as microprocessors, communication and network processors, and so forth), system memory, peripherals, and other hardware components within a system. For example, the communication fabric 304 may be implemented with one or more buses or a crossbar switch.The memory 302 and the persistent storage 305 are computer readable storage media. In this embodiment, memory 302 includes random access memory (RAM). In general, the memory 302 may comprise any suitable volatile or non-volatile computer readable storage medium. Cache 303 is fast memory that increases the performance of processors 301 by storing recently accessed data and data near recently accessed data from memory 302.Program instructions and data used to implement embodiments of the present invention may be stored in persistent memory 305 and memory 302 to be executed by one or more of the respective processors 301 via cache 303. In one embodiment, persistent storage 305 includes a magnetic hard disk drive. Alternatively or in addition to a magnetic hard disk drive, persistent storage 305 may include a solid state disk, a semiconductor storage unit, a read only memory (ROM), an erasable programmable read only memory (EPROM), a flash memory, or any other computer readable storage medium capable of storing program instructions or digital information.The media used by the permanent memory 305 may also be removable. For example, a removable hard disk may be used for persistent storage 305. Other examples include optical and magnetic hard drives, USB sticks, and drive-mounted smart cards for transfer to another computer readable storage medium also forming part of permanent storage 305.The communication device 307 provides communication with other data processing systems or devices in these examples. In these examples, communication device 307 includes one or more network interface cards. The communication device 307 may establish communication using either physical or wireless communication links or both. Program instructions and data used to carry out embodiments of the present invention may be downloaded to the persistent storage 305 via the communication device 307.The I / O interface(s) 306 enable / enable input and output of data to other devices that can be connected to each computer system. For example, the I / O interface 306 may connect to external devices 308 such as a keyboard, keypad, touch screen, and / or other suitable input device. The external devices 308 may also include portable computer readable storage media such as USB sticks, portable optical or magnetic hard drives, and memory cards. Software and data used to carry out embodiments of the present invention may be stored on such portable computer readable storage media and loaded into persistent storage 305 via I / O interface(s) 306. The I / O interface(s) 306 is(are) also connected to the display 309.The display 309 provides a mechanism for presenting data to a user and may be, for example, a computer monitor.The programs described herein are fixed based on the application for which they are implemented in a particular embodiment of the invention. However, it should be appreciated that any particular program nomenclature is used herein for convenience only, and the invention is accordingly not limited to exclusive use in a particular application that is recognized and / or implied by such nomenclature.The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.The computer readable storage medium may be a physical device that can retain and store instructions for use by a system for executing instructions. The computer readable storage medium may be, for example, but is not limited to, an electronic storage unit, a magnetic storage unit, an optical storage unit, an electromagnetic storage unit, a semiconductor storage unit, or any suitable combination thereof. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a removable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions stored thereon, and any suitable combination thereof. A computer readable storage medium, as used herein, is not intended to be transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through a wire.Computer readable program instructions described herein may be downloaded from a computer readable storage medium to respective data processing / processing devices or via a network such as the Internet, a local area network, a wide area network, and / or a wireless network to an external computer or storage device. The network may include copper transmission cables, lightwave transmission conductors, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing unit receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the corresponding computing / processing unit.Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, via the Internet using an Internet Service Provider). In some embodiments, electronic circuits, including, for example, programmable logic circuits, field programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuits to perform aspects of the present invention.Aspects of the present invention are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It is noted that each block of the flowcharts and / or the block diagrams, and combinations of blocks in the flowcharts and / or the block diagrams, may be executed by computer readable program instructions.These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions executed via the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions / steps specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions may also be stored on a computer readable storage medium that can control a computer, programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored thereon comprises an article of manufacture including instructions that implement aspects of the function / step specified in the flowchart and / or block diagrams block or blocks.The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of process steps to be performed on the computer or other programmable apparatus or other device to produce a computer executed process, such that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / steps specified in the flowchart and / or block diagram block or blocks.The flowchart and block diagrams in the figures (i.e., FIG.) illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions that include one or more executable instructions for executing the specified logical function(s). In some alternative implementations, the functions indicated in the block may occur in a different order than shown in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order depending on the appropriate functionality. It is further noted that each block of the block diagrams and / or the flowcharts, as well as combinations of blocks in the block diagrams and / or the flowcharts, may be implemented by special purpose hardware-based systems that perform the specified functions or steps, or perform combinations of special purpose hardware and computer instructions.The descriptions of the various embodiments of the present invention are illustrative, but do not claim completeness or limitation to the disclosed embodiments. Numerous modifications and variations will be apparent to those skilled in the art without departing from the scope of the invention. The terminology used herein was chosen to best explain the principles of the embodiment, the practical application, or the technical improvement over the technologies found in the market, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

A computer-implemented method for multi-factor authentication, the computer-implemented method comprising: generating an evaluation mask (206) over one or more modified elements on a modified image, the modified image being generated by a generative advanced network, GAN; creating an evaluation grid by comparing an original image with the modified image to identify different pixels between the original image and the modified image; overlaying the evaluation mask over the identified different pixels on the modified image; displaying the modified image (208) to a user as a request for multi-factor authentication, the user being prompted to provide a response identifying one or more modifications in the modified image; calculating a score (214) from a comparison of the user's response to the score mask to validate the user's response; and in response to reaching or exceeding a predetermined threshold, checking user's entitlement and granting user access to data or other resources.The computer-implemented method of claim 1, wherein comparing the user's response to the scoring mask comprises: comparing pixels in the original image to pixels of the modified image related to the user's response.The computer-implemented method of claim 1, further comprising: generating, by the GAN, the modified image from the original image, wherein generating the modified image comprises: editing the original image, wherein the editing comprises at least one of: changing objects, people, colors, brightness, age of the people, changing walls, changing clothing, and fashion in the original image.The computer-implemented method of claim 1, wherein displaying the modified image as a multi-factor authentication prompt to the user further comprises: issuing a prompt in response to instructing the user to identify the one or more modified elements or areas in the modified image by tapping, drawing, or clicking on the one or more modified elements or areas in the modified image.The computer-implemented method of claim 1, further comprising: calculating the score from a plurality of response attempts of the user to validate a detection of the user, wherein the plurality of response attempts are based on a plurality of security prompts each using a different modified image selected from a plurality of modified images.The computer-implemented method of claim 1, wherein calculating an evaluation score based on a comparison further comprises: comparing the user's response to the evaluation mask with respect to one or more changes to the original image.The computer-implemented method of claim 1, further comprising: determining that the user's credential is verified based on the calculated score, wherein the score is within or above a predetermined threshold, and wherein a binary credential decision is sent to a platform to provide the user with access to the data or other resources.A computer program product for multi-factor authentication, the computer program product comprising: one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising: program instructions for generating an evaluation mask over one or more modified elements on a modified image, the modified image being generated by a generative advanced network, GAN; program instructions for generating an evaluation grid by comparing an original image with the modified image to detect different pixels between the original image and the modified image; program instructions for overlaying the evaluation mask over the detected different pixels on the modified image; Program instructions for displaying the modified image as a request for multi-factor authentication to a user, the user being requested to provide a response identifying one or more modifications in the modified image; program instructions for calculating an assessment score based on a comparison of the response of the user with the assessment mask to validate the response of the user; and in response to reaching or exceeding a predetermined threshold, program instructions for checking the authentication of the user and granting user access to data or other resources.The computer program product of claim 8, wherein comparing the user's response to the scoring mask comprises: program instructions for comparing pixels in the original image with pixels of the modified image related to the user's response.The computer program product of claim 8, further comprising: program instructions for generating, by the GAN, the modified image from the original image, wherein generating the modified image comprises: program instructions for processing the original image, wherein the processing comprises at least one of: changing objects, persons, colors, brightness, age of the persons, changing walls, changing clothing, and mode in the original image.The computer program product of claim 8, wherein displaying the modified image as a multi-factor authentication prompt to the user further comprises: program instructions to issue a prompt in response instructing the user to recognize the one or more altered elements or areas in the altered image by tapping, drawing, or clicking on the one or more altered elements or areas in the altered image.The computer program product of claim 8, further comprising: program instructions to calculate the score based on a plurality of response attempts of the user to validate a detection of the user, wherein the plurality of response attempts are based on a plurality of security prompts each using a different modified image selected from a plurality of modified images.The computer program product of claim 8, wherein calculating a score based on a comparison further comprises: program instructions to compare the user's response to the scoremask with respect to one or more changes to the original image.The computer program product of claim 8, further comprising: program instructions for determining that the user's credential is verified based on the calculated score, wherein the score is within or above a predetermined threshold, and wherein a binary credential determination is sent to a platform to provide the user with access to the data or other resources.A computer system for multi-factor authentication, the computer system comprising: one or more computer processors (301); one or more computer readable storage media; program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising: program instructions for generating an evaluation mask via one or more modified elements on a modified image, the modified image being generated by a generative adventer network, GAN; program instructions for creating an evaluation grid by comparing an original image with the modified image to detect different pixels between the original image and the modified image; program instructions for imposing the evaluation mask on the detected different pixels on the modified image; Program instructions for displaying the modified image as a request for multi-factor authentication to a user, the user being requested to give a response identifying one or more modifications in the modified image; program instructions for calculating an assessment score based on a comparison of the response of the user with the assessment mask to validate the response of the user; and responsive to the assessment score, reaching or exceeding a predetermined threshold, program instructions for checking authentication of the user and granting user access to data or other resources.The computer system of claim 15, wherein comparing the user's response to the scoring mask comprises: program instructions for comparing pixels in the original image to pixels of the modified image related to the user's response.The computer system of claim 15, further comprising: program instructions for generating, by the GAN, the modified image from the original image, wherein generating the modified image comprises: program instructions for processing the original image, wherein the processing comprises at least one of: changing objects, persons, colors, brightness, age of the persons, changing walls, changing clothing, and fashion in the original image.The computer system of claim 15, wherein displaying the modified image as a request for multi-factor authentication to the user further comprises: program instructions to issue a request in response to instructing the user to recognize the one or more altered elements or areas in the altered image by tapping, drawing, or clicking on the one or more altered elements or areas in the altered image.The computer system of claim 15, further comprising: program instructions to calculate the score based on a plurality of response attempts of the user to validate a detection of the user, wherein the plurality of response attempts are based on a plurality of security prompts each using a different modified image selected from a plurality of modified images.The computer system of claim 15, further comprising: program instructions for comparing the user's response to the scoring mask with respect to one or more changes in the original image; and program instructions for determining that the user's entitlement is verified based on the calculated score, wherein the score is within or above a predetermined threshold, and wherein a binary entitlement verification determination is sent to a platform to permit the user access to the data or other resources.

Images