Abstract: A method includes generating a first vector associated with a token using a first set of parameters of a first learning model based on the token, determining a prediction indicating that the token is associated with a first label based on a set of clustering criteria, the first vector, vectors of a first vector set, and vectors of a second vector. The method includes generating a perturbed vector associated with a second label by modifying a value of the first vector and updating the second vector set to comprise the perturbed vector. The method also includes generating a synthesized token associated with the second vector set based on the perturbed vector using a second set of parameters of the first learning model and training a second learning model based on the synthesized token.

Abstract: A device may receive a preauthorization associated with missed transaction prevention for a transaction account of a user, wherein the missed transaction prevention involves preventing a missed transaction associated with merchant accounts of the user. The device may monitor a transaction log of the transaction account and identify a transaction pattern associated with a merchant account based on a plurality of historical transactions identified in the transaction log related to the merchant account. The device may determine that a historical transaction of the plurality of historical transactions is not designated for automatic execution and that an execution of an upcoming transaction corresponding to the plurality of historical transactions is not scheduled. The device may cause an account transaction associated with the upcoming transaction to be automatically executed before a transaction period expiration, associated with the merchant account, passes.

Abstract: Exemplary embodiments may use word embeddings to enhance scanning of programming code scripts for sensitive subject matter, such as confidential subject matter. The scanning may be performed by a neural network in some exemplary embodiments. The neural network initially may be trained on a corpus of programming code scripts to identify keywords relating to sensitive subject matter, such as passwords, tokens or credentials. The neural network may not only identify instances of the keywords but also may identify related terms as well. The output of the scan may be a ranked list of terms in the programming code script that may relate to sensitive subject matter.

Abstract: Techniques for providing a real-time service that protects personal data of clients from customer service agents are provided. Customer data that includes personal data indicative of sensitive information of a customer can be received from the customer. The personal data within the received customer data can be detected and a token that does not include the sensitive information of the customer can be generated. The personal data and the generated token can be stored along with data indicating a relationship between the token and the personal data. The personal data in the received customer data can be replaced by the token to form modified customer data. The modified customer data can be provided to a customer service representative. The token within the modified customer data can later be detected and associated with the personal data without revealing the personal data to the customer service representative.

Abstract: Systems and methods for dynamically concealing sensitive information in a shared screen session of a video conference are disclosed. The system may establish communication with one or more computing devices active in a video conference in which each computing device may switch between a screen share mode and a video mode. The system may determine that one or more articles of sensitive information are visible in a graphical user interface associated with a first computing device of the plurality of computing devices. The system may receive a first signal from the first computing device that indicates a first intent of a host associated with the first computing device to switch the screen share mode which includes sharing the first graphical user interface with the one or more computing devices during the video conference. In response to the first signal, the system may execute one or more privacy actions.

Abstract: Systems as described herein may label data to preserve privacy. An annotation server may receive a document comprising a collection of text representing a plurality of confidential data from a first computing device. The annotation server may convert the document to a plurality of text embeddings. The annotation server may input the text embeddings into a machine learning model to generate a plurality of synthetic images, and receive a label for each of the plurality of synthetic images from a third-party labeler. Accordingly, the annotation server may send the confidential data and the corresponding labels to a second computing device.

Abstract: A non-transitory computer-readable storage medium storing computer-readable program code executable by a processor to receive a transaction request from a user interface, and receive a user-identifier from the user interface, and the user-identifier associated with a user. The program code may be executable to send a first non-audible sound signal to initiate a multifactor authentication process during a first interval, and send a second non-audible sound signal during a second interval, where the second non-audible sound signal comprises a predetermined frequency pattern, associated with the user. The program code may also be executable to receive a third non-audible sound signal, where the third non-audible sound signal, at least in part, is utilized to determine whether to complete the transaction request or not. The first non-audible sound signal, the second non-audible sound signal, and the third non-audible sound signal may comprise a frequency greater than 15 kHz.

Abstract: System and devices for live captioning events is disclosed. The system may receive event calendar data and a first plurality of caption files and preselect a first caption file based on the event calendar data. The system may then access an audiovisual recorder of a user device, and receive a first feedback from the recorder. The system may then determine whether the first caption file matches the first feedback. When there is a match, the system may determine a first synchronization between the caption file and the feedback. When there is no match, the system may determine if there is a match with a second caption file of the first plurality of caption files and determine a second synchronization. When the second caption file does not match, the system may receive at least a third caption file over a mobile network and determine a third synchronization for display.

Abstract: Systems and methods for determining neural network brittleness are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a modeling request comprising a preliminary model and a dataset. The operations may include determining a preliminary brittleness score of the preliminary model. The operations may include identifying a reference model and determining a reference brittleness score of the reference model. The operations may include comparing the preliminary brittleness score to the reference brittleness score and generating a preferred model based on the comparison. The operations may include providing the preferred model.

Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second sub set.

Abstract: Systems and methods for generating synthetic data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a dataset including time-series data. The operations may include generating a plurality of data segments based on the dataset, determining respective segment parameters of the data segments, and determining respective distribution measures of the data segments. The operations may include training a parameter model to generate synthetic segment parameters. Training the parameter model may be based on the segment parameters. The operations may include training a distribution model to generate synthetic data segments. Training the distribution model may be based on the distribution measures and the segment parameters.

Abstract: Apparatuses, systems and methods are described herein for separately collecting and storing form contents. Different information may be collected from a user on a form. Based on determining that portions of the form request a first type of information, an extended reality (XR) environment may be provided to the user. The user may provide the first type information via an input method in the XR environment. The user may provide a second type of information using a different input method outside of the XR environment. The first type of information may be processed and stored in a different database as compared to the second type of information. The database storing the first type of information may have a higher security standard than the database storing second type of information.

Abstract: The disclosed systems and methods may receive a first salted password having a first password, a first user device identifier, and a first browser identifier, extract the first password, the first user device identifier, and the first browser identifier from the first salted password, and determine whether the first password, the first user device identifier, and the first browser identifier respectively match a stored first password, a stored first user device identifier, and a stored first browser identifier. The systems may grant the request to access the one or more resources for the first user device or perform other actions depending on whether the first password, the first user device identifier, and the first browser identifier respectively match the stored first password, the stored first user device identifier, and the stored first browser identifier.

Abstract: Systems and methods for generating synthetic data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a dataset including time-series data. The operations may include generating a plurality of data segments based on the dataset, determining respective segment parameters of the data segments, and determining respective distribution measures of the data segments. The operations may include training a parameter model to generate synthetic segment parameters. Training the parameter model may be based on the segment parameters. The operations may include training a distribution model to generate synthetic data segments. Training the distribution model may be based on the distribution measures and the segment parameters.

Abstract: Various embodiments are directed to a password security warning system. An artificial neural network or other types of models may be used to determine whether a password that is created, input, or proposed by a user via an interface includes one or more predictable or typical transformations or combinations of characters derived from user-specific information. Based on the determination, a warning may be provided to the user.

Abstract: Systems and methods for selectively obscuring data in a digital statement are disclosed. The systems and methods can relate to multiple user accounts that access a shared account. The systems can include means to determine which account completed a transaction. Device location tracking and hardware characteristics of the devices can be used to determine which account completed the transaction. Information related to transactions that fall outside of expected spend categories can be selectively obscured on the digital statement of the non-transacting account. The information related to the transaction can be selectively viewable by non-transacting account.

Abstract: Disclosed embodiments may include a method that includes setting an influence level for each index that a neural network can accept in one sample to a same level for a neural network, receiving a training corpus including training input samples and a corresponding correct training prediction samples, generating, using the neural network, prediction samples, identifying an accuracy for each index by comparing the prediction samples with the corresponding correct training prediction samples, adjusting the influence level for each index based on the accuracy for each index, identifying one or more poorly accurate indexes for the neural network, receiving a first input sample including one or more characters, generating one or more normalized first input samples by applying one or more buffers to the one or more poorly accurate indexes, and generating, using the neural network, a categorization of each character in the one or more normalized first input samples.

Abstract: A device detects a communication involving a user associated with an account and a service representative, and sends, to a user device associated with the account, an authentication notification that causes the user device to display an authentication field for the user. The device sends, to a service representative device associated with the service representative, a message that indicates that the service representative is to request, via the communication, the user to enter personal information associated with the user into the authentication field, where the user device is configured to generate a first authentication code based on a user input received from the user device in the authentication field. The device generates a second authentication code based on personal information associated with the account from a data structure, receives the first authentication code, and performs an action based on the first authentication code and the second authentication code.

Abstract: In some embodiments, gaze-tracking-based image downscaling for multi-party video communication may be provided. In some embodiments, a set of gaze locations may be received from a set of receiving devices during concurrent video communication sessions between the receiving devices and a sending device. Different collections of positions may be determined based on the gaze locations, and, for each such collection, a spatial indicator (e.g., a bounded region) may be determined. A first downscaled encoding of the source image (from the sending device) may be generated based on the first spatial indicator, and a second downscaled encoding of the source image may be generated based on the second spatial indicator, etc. The downscaled encodings may then be sent to the respective receiving devices during the concurrent video communication sessions.

Abstract: The present disclosure relates to systems and methods for parsing unstructured data with neural networks. In one implementation, a system for parsing unstructured data may include at least one processor and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the system to: receive unstructured data; apply a classifier to the unstructured data to identify a type of the unstructured data; based on the identification, select a corresponding neural network; apply the selected neural network to the unstructured data to obtain structured data; and output the structured data.