Abstract: Systems and methods for leveraging smart glasses for identifying vulnerabilities in application source code is provided. The smart glasses may be configured to scan the code from a user interface (“UI”) linked to an internal development platform and project the scanned code on a display of the smart glasses. Using deep learning, the smart glasses may be enabled to identify one or more vulnerabilities within the scanned application source code. The smart glasses may link a vulnerability classification code for each identified vulnerability. The smart glasses may generate a vulnerability report file including the scanned application source code, each identified vulnerability and its linked vulnerability classification code and transfer the vulnerability report file to a source code repository within the internal development platform. The scanned application source code may be matched to the original application source code and further separate the marched original application source code for assessment.

Abstract: The present invention provides topical compositions comprising a combination ascorbic acid, caffeine, an inorganic salt, and water that are single aqueous phase compositions.

Abstract: Aspects of the disclosure relate to a smart contactless card to detect real-time suspicious card readers or other fraudulent devices. Prior to a transaction, the smart contactless card detects suspicious card readers or fraudulent devices. An alert may be generated upon detection of any suspicious or fraudulent card reader. In some arrangements, the smart contactless card may utilize machine learning models or machine learning capabilities to detect suspicious card readers. The smart contactless card may pair with other smart contactless cards to detect and alert users to suspicious card readers or other fraudulent devices. The paired smart contactless cards may share information regarding suspicious card readers or fraudulent devices over a semi-autonomous data-sharing network. A vulnerability score may be generated and used to determine if a card reader or other payment device is suspicious.

Abstract: The inventive subject matter is directed to pest detection systems that implement infrared emitters with detectors that look for variations in incident light indicative of wingbeats from various pests. Emitters and detectors are placed on one or more printed circuit boards such that infrared light projected from an emitter can be received by one or more detectors. Based on signal generated by a detector, systems of the inventive subject matter can determine whether a pest has flown between an emitter and detector. To save on power, emitter, detectors, or both can be driven by pulse width modulation. Methods of the inventive subject matter are directed to determining pest presence via signal filtering and interpretation.

Abstract: The inventive subject matter is directed to pest detection systems that implement infrared emitters with detectors that look for variations in incident light indicative of wingbeats from various pests. Emitters and detectors are placed on one or more printed circuit boards such that infrared light projected from an emitter can be received by one or more detectors. Based on signal generated by a detector, systems of the inventive subject matter can determine whether a pest has flown between an emitter and detector. To save on power, emitter, detectors, or both can be driven by pulse width modulation. Methods of the inventive subject matter are directed to determining pest presence via signal filtering and interpretation.

Abstract: A device configured to obtain group information from a database, to identify a first set of clusters based on the group information, and to determine a first cluster quantity that identifies a number of clusters within the first set of clusters. The device is further configured to obtain user interaction data for user devices, to input the user interaction data into a machine learning model, to receive a second set of clusters from the machine learning model based on the user interaction data, and to determine a second cluster quantity that identifies a number of clusters within the second set of clusters. The device is further configured to determine the second cluster quantity is greater than the first cluster quantity, to identify a cluster that is not present in the first set of clusters, and to modify settings on a user device from within the cluster.

Abstract: A device configured to obtain a first user interaction data at a first time instance for user devices, to obtain a first set of clusters from a machine learning model based on the first user interaction data, and to determine a first cluster quantity for the first set of clusters. The device is further configured to obtain a second user interaction data at a second time instance for the user devices, to obtain a second set of clusters from the machine learning model based on the second user interaction data, and to determine a second cluster quantity for the second set of clusters. The device is further configured to determine the second cluster quantity is greater than the first cluster quantity, to identify a cluster that is not present in the first set of clusters, and to modify settings on a user device from within the cluster.

Abstract: A system receives, from an augmented reality device, a first image of a web application, where the first image shows a first element of the web application. The system receives eye tracking information that indicates eye movements of a user as the user is looking at different elements of the web application. The system determines that the user is looking at a first location coordinate on the first image of the web application. The system determines that the first element is located at the first location coordinate. The system identifies first element attributes associated with the first element. The system generates an augmented reality message comprising the first element attributes. The system generates an augmented reality display in which the augmented reality message is presented as a virtual object. The system transmits the augmented reality display to the augmented reality device.

Abstract: A smart glasses device for initiating a transaction between a first smart card and a second smart card is provided. The smart glasses device may include a camera operable to capture an image of the first smart card and of the second smart card. The smart glasses device may include a display operable to trigger an augmented reality display including a first selectable image of the first smart card and a second selectable image of the second smart card. The camera may further capture a series of motions corresponding to a numerical value inputted in an augmented fillable field, a selection of the second selectable image of the second smart card, and a movement dragging the selected second selectable image from a first location to a second location positioned on top of the first selectable image of the first smart card. The positioning automatically triggering an initiation of the transaction.

Abstract: An apparatus can include universal serial bus type C (USB-C) connection circuitry. The apparatus can also include input/output (I/O) circuitry coupled to the USB-C connection circuitry. The I/O circuitry can receive a power signal over the USB-C connection circuitry. The apparatus can include baseband circuitry to initiate wireless wide area network (WWAN) communication responsive to receiving a wake signal from the I/O circuitry. The WWAN communication can include messages received from the USB-C connection circuitry. Other apparatuses, systems, and methods are described.

Abstract: Aspects of the disclosure relate to ATM monitoring and enhancement. A computing platform may detect ATM performance information from an ATM. The computing platform may validate the ATM performance information against baseline ATM performance information. Based on validating the ATM performance information, the computing platform may generate a digital twin for the ATM, and may input the digital twin into a deep learning model for anomaly detection. Based on identifying that the digital twin includes an anomaly, the computing platform may update and simulate the updated digital twin. The computing platform may determine, using smart contracts stored on a distributed ledger, whether or not an update to the ATM based on the updated digital twin is approved. Based on determining that the update to the ATM is approved, the computing platform may direct the ATM to perform a configuration update based on the updated digital twin.

Abstract: Aspects of the disclosure relate to ATM monitoring and enhancement. A computing platform may detect ATM performance information from an ATM. The computing platform may validate the ATM performance information against baseline ATM performance information. Based on validating the ATM performance information, the computing platform may generate a digital twin for the ATM, and may input the digital twin into a deep learning model for anomaly detection. Based on identifying that the digital twin includes an anomaly, the computing platform may update and simulate the updated digital twin. The computing platform may determine, using smart contracts stored on a distributed ledger, whether or not an update to the ATM based on the updated digital twin is approved. Based on determining that the update to the ATM is approved, the computing platform may direct the ATM to perform a configuration update based on the updated digital twin.

Abstract: A system includes a memory, and a processor. The processor receives a request to register a device. In response, the processor extracts a set of parameters from the device, and stores a baseline record associated with the device, which includes the set of parameters, in the memory. The processor determines that an update to the device modified the set of parameters. In response, the processor extracts the modified set of parameters from the device, and stores a new record associated with the device, which includes the modified set of parameters, in the memory. The baseline record was used to validate an identity of the device prior to the processor determining that the update modified the set of parameters. The new record is used to validate the identity of the device subsequent to the processor determining that the update modified the set of parameters.

Abstract: A system includes a memory and a processor. The memory stores a baseline record associated with a device, which includes a set of parameters that were extracted from the device. The processor receives a request from the device to initiate a communication. In response to receiving the request to initiate the communication, the processor determines that an update to the device has modified the set of parameters of the device. In response to determining that that the update has modified the set of parameters, the processor extracts the modified set of parameters from the device, and stores a new record associated with the device in the memory, which includes the modified set of parameters extracted from the device. The processor additionally uses the new record to validate the request. In response to validating the request, the processor transmits the communication.

Abstract: A system includes a memory and a processor. The memory stores a plurality of records associated with a device and a machine learning algorithm. The plurality of records includes a first record and a second record. The first record includes a first set of parameters extracted from the device at a first time. The second record includes a second set of parameters extracted from the device at a second time, with a difference between the first set of parameters and the second set of parameters resulting from of an update to the device. The machine learning algorithm is configured to determine a probability that the update was unauthorized. The processor executes the machine learning algorithm, and determines that the probability is greater than a threshold. In response to determining that the probability is greater than the threshold, the processor rejects a request transmitted by the device.

Abstract: Systems, methods, and apparatus are provided for intelligent dynamic rendering of an augmented reality (AR) display. An AR device may capture an image of a physical environment. Feature extraction combined with deep learning may be used for object recognition and detection of changes in the environment. Contextual analysis of the environment based on the deep learning outputs may enable improved integration of AR rendering with the physical environment in real time. A BLE beacon feed may provide supplemental information regarding the physical environment. The beacon feed may be extracted, classified, and labeled based on user interests using machine learning algorithms. The beacon feed may be paired with the AR advice to incorporate customized location-based graphics and text into the AR display.

Abstract: An artificial intelligence/machine learning (AI./ML) model decisioning and rectification system is configured to allow a user to challenge decisions output by systems processing AI/ML models. The user interacts with the AI/ML model decisioning and rectification system, directly or via another computing device, to trigger AI/ML training data acquisition from multiple regional data stores processing the AI/ML model. A data acquisition module is composite apparatus that intelligently fetches training data sets applicable to the particular AI/ML model in a distributed network and initiates intelligent retraining of the AI/ML model based on an aggregated regional training data set.

Abstract: A system for detecting security threats in automated teller machines (ATMs) extracts baseline features from a first set of signals received from a first ATM, when the first ATM is initiated to operate. The baseline features represent a unique electrical signature of the first ATM. The system extracts test features from a second set of signals received from the first ATM, when the first ATM is in operation. The system determines whether there is a deviation between the test features and baseline features. If the system detects the deviation, the system determines that the first ATM is associated with a particular anomaly that makes the first ATM vulnerable to unauthorized access. The system determines that a second ATM is associated with the particular anomaly if the system detects the deviation between baseline features and test features associated with the second ATM.

Abstract: An automated teller machine (ATM) receives a first set of signals from components of the ATM. The first set of signals includes intercommunication electrical signals between the components of the ATM and electromagnetic radiation signals propagated from the components of the ATM. The ATM extracts baseline features from the first set of signals. The baseline features represent a unique electrical signature of the ATM. The ATM extracts test features from a second set of signals received from the component of the ATM. The ATM determines whether there is a deviation between the test features and baseline features. If the ATM detects the deviation, the ATM determines that the ATM is associated with a particular anomaly that makes the ATM vulnerable to unauthorized access.

Abstract: Systems, methods and apparatus are provided for a Dynamic Group Session Data Access Protocol. The system may monitor participant input in a group interactive session. The system may be trained to monitor and understand the group environment and predict intent of the participant discussion and may predict relevant data. The system may be used by a single participant or by multiple participants. The system may determine the access level of the participants. The system may determine the access level of the data. The system may compare the access level of the participants with the access level of the data. The system may dynamically mask the data if the access level of the participants does not match the access level of the data. The system may create customized views of the data for each participant based on the participant's access level and the access level of the data.