Abstract: In some implementations, a terminal device may obtain exchange information associated with an exchange initiated at the terminal device. The exchange information may identify a medium used in the exchange. The terminal device may be configured to present a terminal-side user interface for performing a signing operation of the exchange. The terminal device may selectively obtain user information associated with the medium used in the exchange. The user information may identify a user device associated with the medium. The terminal device may transmit, to the user device and based on obtaining the user information, presentation information that identifies content for a user-side user interface for performing the signing operation at the user device. The terminal device may receive, from the user device, signing information associated with a performance of the signing operation at the user device via the user-side user interface.

Abstract: In some implementations, a server device may receive, from a client device, a login credential associated with a user and a request to access a resource. The server device may identify a confidant associated with the user and a confidant device associated with the confidant, wherein the confidant device is different from a user device associated with the user. The server device may transmit, to the confidant device, a request to verify an identity of the user. The server device may determine whether a verification of the identity of the user is received from the confidant device. The server device may grant or deny access to the resource based on determining whether the verification of the identity of the user is received from the confidant device.

Abstract: In an embodiment, the systems and methods discussed herein are related to generating, via a processor, a Markov Distribution Problem (MDP), the MDP including a state space, an action space, a transition function, a reward function, and a discount factor. A reinforcement learning (RL) model is applied, via the processor, to the MDP to generate a RL agent. An input data associated with a first user is received at the RL agent. At least one counterfactual explanation (CFE) is generated via the processor and by the RL agent and based on the input data. A representation of the at least one CFE and at least one recommended remedial action is caused to transmit, via the processor, to at least one of a compute device of the first user or a compute device of a second user different from and associated with the first user.

Abstract: A system may comprise one or more processors, a memory in communication with the one or more processors, and storing instructions, that when executed by the one or more processors, are configured to cause the system to perform a method for decrypting an encrypted message. The method may include providing an encrypted code to a first user, receiving one or more first images comprising the encrypted code from a first user device associated with the first user. The method may include determining whether the first user device is a trusted device for the encrypted code. The method may include mapping the encrypted code to a first sequence of alphanumeric characters associated with the encrypted code. The method may include providing the first decrypted code comprising the first sequence of alphanumeric characters to the first user device for display in augmented reality proximate the encrypted code.

Abstract: In some implementations, a terminal device may obtain exchange information associated with an exchange initiated at the terminal device. The exchange information may identify a medium used in the exchange. The terminal device may be configured to present a terminal-side user interface for performing a signing operation of the exchange. The terminal device may selectively obtain user information associated with the medium used in the exchange. The user information may identify a user device associated with the medium. The terminal device may transmit, to the user device and based on obtaining the user information, presentation information that identifies content for a user-side user interface for performing the signing operation at the user device. The terminal device may receive, from the user device, signing information associated with a performance of the signing operation at the user device via the user-side user interface.

Abstract: In some implementations, a terminal device may obtain exchange information associated with an exchange initiated at the terminal device. The exchange information may identify a medium used in the exchange. The terminal device may be configured to present a terminal-side user interface for performing a signing operation of the exchange. The terminal device may selectively obtain user information associated with the medium used in the exchange. The user information may identify a user device associated with the medium. The terminal device may transmit, to the user device and based on obtaining the user information, presentation information that identifies content for a user-side user interface for performing the signing operation at the user device. The terminal device may receive, from the user device, signing information associated with a performance of the signing operation at the user device via the user-side user interface.

Abstract: A computing system may generate a first set of importance metrics (e.g., scores or values) for a model. The importance metrics may be generated using an explainable artificial intelligence technique, and an individual importance metric may indicate how influential a corresponding feature is for a decision made by a model. The computing system may determine an important feature and create a modified dataset by removing the important feature from the dataset. The computing system may train the model on the modified dataset and evaluate the performance of the model to determine the effect of removing the feature (e.g., which may indicate how important the feature is to output generated by the model). This process may be repeated for additional features and additional performance metrics may be obtained.

Abstract: In some implementations, a server device may receive, from a client device, a login credential associated with a user and a request to access a resource. The server device may identify a confidant associated with the user and a confidant device associated with the confidant, wherein the confidant device is different from a user device associated with the user. The server device may transmit, to the confidant device, a request to verify an identity of the user. The server device may determine whether a verification of the identity of the user is received from the confidant device. The server device may grant or deny access to the resource based on determining whether the verification of the identity of the user is received from the confidant device.

Abstract: In some implementations, a server device may receive, from a client device, a login credential associated with a user and a request to access a resource. The server device may identify a confidant associated with the user and a confidant device associated with the confidant, wherein the confidant device is different from a user device associated with the user. The server device may transmit, to the confidant device, a request to verify an identity of the user. The server device may determine whether a verification of the identity of the user is received from the confidant device. The server device may grant or deny access to the resource based on determining whether the verification of the identity of the user is received from the confidant device.

Abstract: A system may comprise one or more processors, a memory in communication with the one or more processors, and storing instructions, that when executed by the one or more processors, are configured to cause the system to perform a method for decrypting an encrypted message. The method may include providing an encrypted code to a first user, receiving one or more first images comprising the encrypted code from a first user device associated with the first user. The method may include determining whether the first user device is a trusted device for the encrypted code. The method may include mapping the encrypted code to a first sequence of alphanumeric characters associated with the encrypted code. The method may include providing the first decrypted code comprising the first sequence of alphanumeric characters to the first user device for display in augmented reality proximate the encrypted code.

Abstract: Aspects described herein may include detecting, by a browser extension, a checkout page for the purchase of an item using a credit card. Product transaction data and a warranty expiration date of the purchased item may be retrieved, and the warranty expiration date of the purchased item may be stored. Creation of a notification to be sent to the user prior to the warranty expiration may be scheduled. The notification, which includes the warranty expiration date of the purchased item, may then be forwarded to the user through the browser extension.

Abstract: In some implementations, a server device may receive, from a client device, a login credential associated with a user and a request to access a resource. The server device may identify a confidant associated with the user and a confidant device associated with the confidant, wherein the confidant device is different from a user device associated with the user. The server device may transmit, to the confidant device, a request to verify an identity of the user. The server device may determine whether a verification of the identity of the user is received from the confidant device. The server device may grant or deny access to the resource based on determining whether the verification of the identity of the user is received from the confidant device.

Abstract: In an embodiment, the systems and methods discussed herein are related to generating, via a processor, a Markov Decision Process (MDP), the MDP including a state space, an action space, a transition function, a reward function, and a discount factor. A reinforcement learning (RL) model is applied, via the processor, to the MDP to generate a RL agent. An input data associated with a first user is received at the RL agent. At least one counterfactual explanation (CFE) is generated via the processor and by the RL agent and based on the input data. A representation of the at least one CFE and at least one recommended remedial action is caused to transmit, via the processor, to at least one of a compute device of the first user or a compute device of a second user different from and associated with the first user.

Abstract: In some implementations, a terminal device may obtain exchange information associated with an exchange initiated at the terminal device. The exchange information may identify a medium used in the exchange. The terminal device may be configured to present a terminal-side user interface for performing a signing operation of the exchange. The terminal device may selectively obtain user information associated with the medium used in the exchange. The user information may identify a user device associated with the medium. The terminal device may transmit, to the user device and based on obtaining the user information, presentation information that identifies content for a user-side user interface for performing the signing operation at the user device. The terminal device may receive, from the user device, signing information associated with a performance of the signing operation at the user device via the user-side user interface.

Abstract: A vascular snare system and method for extracting elongated objects such as pacemaker pacing leads or defibrillator leads from the vasculature of a patient are provided. The system utilizes a sheath having a lumen through which two wire elements are deployed to snare and extract a lead. Each wire element has a magnet disposed at its distal end. The wire elements may be manipulated to form a closed loop transversely around a midsection or central portion of the body of the lead by coupling the magnets to each other. The wire elements may then be utilized to extract the lead from the vasculature of the patient through the lumen.

Abstract: A vascular snare system and method for extracting elongated objects such as pacemaker pacing leads or defibrillator leads from the vasculature of a patient are provided. The system utilizes a sheath having a lumen through which two wire elements are deployed to snare and extract a lead. Each wire element has a magnet disposed at its distal end. The wire elements may be manipulated to form a closed loop transversely around a midsection or central portion of the body of the lead by coupling the magnets to each other. The wire elements may then be utilized to extract the lead from the vasculature of the patient through the lumen.