Abstract: Arrangements for universal self-service kiosk fraud detection are provided. A request for a transaction may be received via a self-service kiosk. The financial institution associated with the transaction may be identified as part of a consortium of financial institutions. Accordingly, a machine learning model particular to the consortium may be used to analyze the transaction. The model may output a determination of whether fraud or potential fraud exists in the transaction. In some examples, the machine learning model may be trained using historical transaction data from one or more financial institutions that are part of the consortium. If fraud is detected, one or more security actions associated with the transaction may be identified and executed. Further, one or more additional self-service kiosks that may be impacted by the fraud may be identified and security actions may be identified and transmitted to the one or more additional self-service kiosks for execution.

Abstract: A system for monitoring threat models. The system stores test data that include activity data performed by two or more external sources. The test data includes data from at least one previous threat. The test data is updated with additional test data from at least one of two or more external sources. The additional test data includes new data associated with at least one new threat. The system receives two or more external sources from two or more threat models and implements them in a virtual test environment, which utilizes the two or more threat models to detect at least one previous threat and at least one new threat. When at least one of the two or more threat models does not detect the at least one new threat, an action is performed to modify it.

Abstract: A computing platform may train, using historical information access pattern information, a machine learning model to identify unauthorized information access patterns. The computing platform may obscure internal traffic pattern information, and monitor access of the obscured internal traffic pattern information. The computing platform may generate, by inputting information of the access into the machine learning model, a user evaluation output, and may compare the user evaluation output to a first user evaluation threshold. Based on identifying that the user evaluation output meets or exceeds the first user evaluation threshold, the computing platform may modify traffic routing rules corresponding to the user, which may cause activity by the user to be routed to a secure sandbox for further analysis.

Abstract: Embodiments of the present invention provide a system for identifying and blocking synthetic media based misappropriation attempts associated with electronic communications. The system is configured for identifying initiation of an authentication request from a user device of a user, monitoring and recording user characteristics via the user device, capturing user environment data of the user, via the user device, analyzing either one or both the user characteristics and the user environment data of the user, via an artificial intelligence engine, determining, via the artificial intelligence engine, if the authentication request is a misappropriation attempt based on at least one of the user characteristics and the user environment data, and performing an action comprising authenticating the user based on determining that the authentication request is not a misappropriation attempt or denying authentication of the user based on determining that the authentication request is a misappropriation attempt.

Abstract: Arrangements for universal self-service kiosk fraud detection are provided. A request for a transaction may be received via a self-service kiosk. The financial institution associated with the transaction may be identified as part of a consortium of financial institutions. Accordingly, a machine learning model particular to the consortium may be used to analyze the transaction. The model may output a determination of whether fraud or potential fraud exists in the transaction. In some examples, the machine learning model may be trained using historical transaction data from one or more financial institutions that are part of the consortium. If fraud is detected, one or more security actions associated with the transaction may be identified and executed. Further, one or more additional self-service kiosks that may be impacted by the fraud may be identified and security actions may be identified and transmitted to the one or more additional self-service kiosks for execution.

Abstract: Embodiments of the present invention provide a system for identifying and blocking synthetic media based misappropriation attempts associated with electronic communications. The system is configured for identifying initiation of an authentication request from a user device of a user, monitoring and recording user characteristics via the user device, capturing user environment data of the user, via the user device, analyzing the user characteristics and the user environment data of the user, via an artificial intelligence engine, determining, via the artificial intelligence engine, if the authentication request is a misappropriation attempt based on at least one of the user characteristics and the user environment data, and performing an action comprising authenticating the user based on determining that the authentication request is not a misappropriation attempt or denying authentication of the user based on determining that the authentication request is a misappropriation attempt.

Abstract: A computing platform may train, using historical information access pattern information, a machine learning model to identify unauthorized information access patterns. The computing platform may obscure internal traffic pattern information, and monitor access of the obscured internal traffic pattern information. The computing platform may generate, by inputting information of the access into the machine learning model, a user evaluation output, and may compare the user evaluation output to a first user evaluation threshold. Based on identifying that the user evaluation output meets or exceeds the first user evaluation threshold, the computing platform may modify traffic routing rules corresponding to the user, which may cause activity by the user to be routed to a secure sandbox for further analysis.

Abstract: A computing platform may generate a graphical user interface. The computing platform may embed, into the graphical user interface, steganography, which may include information corresponding to the graphical user interface that is not displayed on the graphical user interface. The computing platform may receive, from a user device of a user, an interface access request and user access credentials. The computing platform may identify, based on the user access credentials, access permissions of the user, which may define portions of the steganography to which the user has access. The computing platform may record, in a change log, interactions of the user with the graphical user interface. The computing platform may compare the interactions in the change log with the access permissions to identify whether or not unauthorized access is detected. Based on detecting the unauthorized access, the computing platform may initiate security actions for the graphical user interface.

Abstract: Aspects related to an amalgamation platform providing concealed detection of code-passing using steganography are provided. An amalgamation platform may train a scoring engine to generate suspicion scores for code snippets and an amalgamation engine to generate execution scenarios for the code snippets. The platform may embed code in base code of a network using steganography. The platform may use the steganographic code to detect transmission of a code snippet. The platform may generate a suspicion score for the code snippet. The platform may update the scoring engine based on identifying the suspicion score satisfies a threshold. The platform may generate execution scenarios for the code snippet. The platform may determine a match between an execution scenario and a malicious code scenario. The platform may identify the code snippet as malicious and update the amalgamation engine based on the match. The platform may initiate security actions based on the match.

Abstract: A computing platform may generate a graphical user interface. The computing platform may embed, into the graphical user interface, steganography, which may include information corresponding to the graphical user interface that is not displayed on the graphical user interface. The computing platform may receive, from a user device of a user, an interface access request and user access credentials. The computing platform may identify, based on the user access credentials, access permissions of the user, which may define portions of the steganography to which the user has access. The computing platform may record, in a change log, interactions of the user with the graphical user interface. The computing platform may compare the interactions in the change log with the access permissions to identify whether or not unauthorized access is detected. Based on detecting the unauthorized access, the computing platform may initiate security actions for the graphical user interface.

Abstract: Aspects related to an amalgamation platform providing concealed detection of code-passing using steganography are provided. An amalgamation platform may train a scoring engine to generate suspicion scores for code snippets and an amalgamation engine to generate execution scenarios for the code snippets. The platform may embed code in base code of a network using steganography. The platform may use the steganographic code to detect transmission of a code snippet. The platform may generate a suspicion score for the code snippet. The platform may update the scoring engine based on identifying the suspicion score satisfies a threshold. The platform may generate execution scenarios for the code snippet. The platform may determine a match between an execution scenario and a malicious code scenario. The platform may identify the code snippet as malicious and update the amalgamation engine based on the match. The platform may initiate security actions based on the match.

Abstract: Embodiments of the present invention provide a system for identifying and blocking synthetic media based misappropriation attempts associated with electronic communications. The system is configured for identifying initiation of an authentication request from a user device of a user, monitoring and recording user characteristics via the user device, capturing user environment data of the user, via the user device, analyzing the user characteristics and the user environment data of the user, via an artificial intelligence engine, determining, via the artificial intelligence engine, if the authentication request is a misappropriation attempt based on at least one of the user characteristics and the user environment data, and performing an action comprising authenticating the user based on determining that the authentication request is not a misappropriation attempt or denying authentication of the user based on determining that the authentication request is a misappropriation attempt.

Abstract: A system for monitoring threat models. The system stores test data that include activity data performed by two or more external sources. The test data includes data from at least one previous threat. The test data is updated with additional test data from at least one of two or more external sources. The additional test data includes new data associated with at least one new threat. The system receives two or more external sources from two or more threat models and implements them in a virtual test environment, which utilizes the two or more threat models to detect at least one previous threat and at least one new threat. When at least one of the two or more threat models does not detect the at least one new threat, an action is performed to modify it.

Abstract: A system is provided for containerization-based countermeasures to cybersecurity vulnerabilities. In particular, the system may generate one or more containers (e.g., virtual environments), where each container may be configured to execute one or more tasks. At least a portion of the containers may be decoy containers that may be executing one or more decoy tasks. The system may then use a randomized process to change which containers are decoy and/or which tasks or jobs are executed within each container. Each container may be associated with a cryptographic key such that each container may be hashed by the system and compared against a reference hash associated with the container. If the hash has changed, the system may determine that the container has been modified and subsequently implement one or more intelligent remediation processes.

Abstract: Aspects related to an amalgamation platform providing concealed detection of code-passing using steganography are provided. An amalgamation platform may train a scoring engine to generate suspicion scores for code snippets and an amalgamation engine to generate execution scenarios for the code snippets. The platform may embed code in base code of a network using steganography. The platform may use the steganographic code to detect transmission of a code snippet. The platform may generate a suspicion score for the code snippet. The platform may update the scoring engine based on identifying the suspicion score satisfies a threshold. The platform may generate execution scenarios for the code snippet. The platform may determine a match between an execution scenario and a malicious code scenario. The platform may identify the code snippet as malicious and update the amalgamation engine based on the match. The platform may initiate security actions based on the match.

Abstract: Remote access to secured containers is provided by a user interface apparatus having an associated receptacle for receiving physical items delivered from and to the remote secured container. Delivery of the physical items to and from the user interface device's receptacle and the secure container may be accomplished by a robotic mechanism or the like. The user of the remote secured container access system pre-registers, such that presentation of the user credentials at the user interface apparatus provides the user options for receiving items for the secured container and delivering items. Moreover, the user credentials are associated with a secure container identifier and access credentials for gaining access to the secured area and/or the secured container, such that presentation of the user credentials provides identification of the secure container and access to the secured area and/or the secured container.

Abstract: A computing platform may generate a graphical user interface. The computing platform may embed, into the graphical user interface, steganography, which may include information corresponding to the graphical user interface that is not displayed on the graphical user interface. The computing platform may receive, from a user device of a user, an interface access request and user access credentials. The computing platform may identify, based on the user access credentials, access permissions of the user, which may define portions of the steganography to which the user has access. The computing platform may record, in a change log, interactions of the user with the graphical user interface. The computing platform may compare the interactions in the change log with the access permissions to identify whether or not unauthorized access is detected. Based on detecting the unauthorized access, the computing platform may initiate security actions for the graphical user interface.

Abstract: Arrangements for universal self-service kiosk fraud detection are provided. A request for a transaction may be received via a self-service kiosk. The financial institution associated with the transaction may be identified as part of a consortium of financial institutions. Accordingly, a machine learning model particular to the consortium may be used to analyze the transaction. The model may output a determination of whether fraud or potential fraud exists in the transaction. In some examples, the machine learning model may be trained using historical transaction data from one or more financial institutions that are part of the consortium. If fraud is detected, one or more security actions associated with the transaction may be identified and executed. Further, one or more additional self-service kiosks that may be impacted by the fraud may be identified and security actions may be identified and transmitted to the one or more additional self-service kiosks for execution.

Abstract: A computing platform may train, using historical information access pattern information, a machine learning model to identify unauthorized information access patterns. The computing platform may obscure internal traffic pattern information, and monitor access of the obscured internal traffic pattern information. The computing platform may generate, by inputting information of the access into the machine learning model, a user evaluation output, and may compare the user evaluation output to a first user evaluation threshold. Based on identifying that the user evaluation output meets or exceeds the first user evaluation threshold, the computing platform may modify traffic routing rules corresponding to the user, which may cause activity by the user to be routed to a secure sandbox for further analysis.

Abstract: Arrangements for a universal self-service kiosk platform are provided. In some aspects, registration data may be received from a plurality of enterprise organizations and may include self-service kiosk configuration data for each enterprise organization. A request to associate a self-service kiosk with a first enterprise organization may be received and may include identification of the first enterprise organization and the self-service kiosk. In response, a self-service kiosk configuration associated with the first enterprise organization may be retrieved and an instruction causing the self-service kiosk to implement the self-service kiosk configuration associated with the first enterprise organization may be generated. The instruction may be transmitted to the self-service kiosk.