Bank of America Corporation

Elvis Nyamwange

Brian Neal Jacobson

Maharaj Mukherjee

Utkarsh Raj

Carl M Benda

Suman Roy Choudhury

Pratap Dande

Rahul Yaksh

Amer Ali

Sailesh Vezzu

Hari Vuppala

Rahul Shashidhar Phadnis

Erik D Dahl

Erik Dahl

Madhukiran Bangalore Ramachandra

Donna Lee Phillips

Vismay Mandloi

Colin Murphy

Vidya Srikanth

Vijay Kumar Yarabolu

Boris Gitlin

Systems, computer program products, and methods are described herein an automated system for restarting large scale cluster supercomputers. The present disclosure is configured to receive a request to reboot a supercomputer cluster, wherein the request comprises a sequence of reboot instructions; determine, using a data integrity engine, whether a current state of the supercomputer cluster meets reboot requirements, wherein the reboot requirements are associated with a core logic of the data integrity engine; and execute the sequence of reboot instructions in an instance where the current state of the supercomputer cluster meets the reboot requirements.

Automated system for restarting large scale cluster supercomputers

Embodiments of the present invention provide a system for analyzing operational parameters of electronic and software components associated with entity applications to detect anomalies. The system is configured for extracting one or more historical images associated with resiliency status of electronic and software components associated with an entity application, analyzing the one or more historical images to generate a pixel wise average of the one or more historical images, generating similarity scores between the one or more historical images, determining a distribution of the similarity scores, receiving a real-time image associated with a current resiliency status of the electronic and software components associated with the entity application, generating a real-time image similarity score for the real-time image, and comparing the real-time image similarity score with the distribution to detect presence of an anomaly.

System and method for analyzing operational parameters of electronic and software components associated with entity applications to detect anomalies

Aspects of the disclosure relate to automatically re-routing multi-cloud holochain data ingestion based on network architecture availability for internet of things (IoT) devices. A computing platform may request information that describes each cloud computing environment of a multi-cloud computing environment to identify the cloud computing environment that may store consumer data. The computing platform may compare the information that describes each cloud computing environment to an enterprise organization's preferences for selecting a cloud computing environment. The cloud computing platform may validate the consumer data and may encrypt the consumer data using public and private key pairs. The computing platform may transmit the encrypted consumer data to the cloud computing environment that satisfies the enterprise organization's preferences.

Automatically re-routing multi-cloud holochain data ingestion based on network architecture availability to internet of things (IoT) devices

A computing platform may train, using historical telemetry state images, an image comparison model to identify matches between telemetry state images. The computing platform may generate a plurality of system alerts corresponding to a period of time. The computing platform may access telemetry data corresponding to the period of time. The computing platform may generate, based on the telemetry data and for a time corresponding to each of the plurality of system alerts, a telemetry state image. The computing platform may input, into the image comparison model, the telemetry state images to identify whether or not any of the plurality of telemetry state images match. Based on detecting a match, the computing platform may consolidate system alerts corresponding to the matching telemetry state images, which may produce a single system alert and may send, to a user device, the single system alert.

System and method for consolidation of alerts and events using image matching of heatmap descriptions of infrastructure status

An apparatus may include conduction of a secure transfer at a point of identification using image recognition and blockchain authentication. The apparatus may include a computer processor, a camera, an image capturing machine, a reference database, an XGBoost image recognition machine learning model, and a blockchain. The computer processor may be an edge computing device. The computer processor may be configured to identify a user at a point of identification by capturing an image, running the Features detection engine to identify sets of features, running the XGBoost image recognition machine learning model to identify labels in the sets of features, and matching the sets of features and labels to a record in the reference database. The computer processor may further be configured to seek user approval on the user's portable device before providing the transfer. Once the user has approved the transfer, the transfer may be recorded in the blockchain.

Automated image detection utilizing a convolutional XGBoost image recognition machine learning model on edge computing with blockchain mobile authentication

Aspects of the disclosure relate to detecting attempts to violate the security of an ATM. A computing system may determine whether an ATM is being used to perform a transaction. Based on the ATM not being used to perform a transaction, images of portions of the ATM may be generated. Estimated dimensions of the ATM may be determined. Digital twin data may be retrieved. The digital twin data may comprise a digital twin representation of the ATM and measured dimensions of the ATM. There may be a determination of whether the estimated dimensions of the ATM match the measured dimensions of the ATM. Based on the estimated dimensions of the ATM not matching the measured dimensions of the ATM, the ATM may be deactivated. Furthermore, a message indicating that the ATM was deactivated may be sent to a validation computing system.

Automated teller machine digital twin with an anti NFC/RFID skimming threat device through mist computation

Aspects of the disclosure relate to outage prevention. A computing platform may train, using historical parameter information and historical outage information, an outage prediction model. The computing platform may receive, from at least one system, current parameter information, and may normalize the current parameter information. The computing platform may convert, using a CNN of the outage prediction model, the normalized current parameter information to a frequency domain. The computing platform may input, into at least one RNN of the outage prediction model, the frequency domain information, to produce a likelihood of outage score. The computing platform may compare the likelihood of outage score to a predetermined outage threshold. Based on identifying that the likelihood of outage score meets or exceeds the predetermined outage threshold, the computing platform may direct the at least one system to execute a performance modification to prevent a predicted outage.

Hybrid neural network for preventing system failure

Virtual machine images may be constantly scanned using background process, to identify current and evolving security risks, such as by optimizing the image scanning a last-in, first-out (LIFO) stack to prioritize most relevant images. Older and/or non-relevant image are removed from the scanning process and removed from use. Virtual machines image prioritization is based on each virtual machine image's current and/or potential usage requirement, where the LIFO stack prioritizes the scanning order. Newly created virtual machine images and/or newly re-activated virtual machine images are placed onto a provisioning queue (first-in, first out) before activation. The virtual machine images active within a host computing environment are processed via a reconciliation process to scan for indications of security vulnerabilities and/or threats to network security. Obsolete or otherwise irrelevant virtual machine images are removed from use via a repository synchronization process.

Virtual machine image management system

Systems, computer program products, and methods are described herein for a machine learning based system for optimized CPU utilization in data transformation. The present disclosure is configured to receive a new data segment; retrieve characteristics of the new data segment; determine, using a trained machine learning model, an encryption algorithm, and a compression algorithm for implementation on the new data segment based on at least the characteristics of the new data segment; determine, using the trained machine learning model, an order of implementation associated with the implementation of the encryption algorithm and the compression algorithm; and implement the encryption algorithm and the compression algorithm on the new data segment in the determined order of implementation.

Machine learning based system for optimized central processing unit (CPU) utilization in data transformation

Systems, methods, and computer program products are provided herein for hyperspectral imaging based electronic authentication resource transfers. An example method includes receiving a resource transfer request associated with at least a first user and receiving hyperspectral image data associated with the first user. The method further includes extracting, via a hyperspectral imaging module, one or more account credentials of the first user from the hyperspectral image data. The method also includes effectuating the resource transfer associated with an account of the first user as defined by the one or more account credentials. The hyperspectral image data may be generated in response to an image capturing operation performed by the hyperspectral imaging module and may be indicative of a hyperspectral image supported by a resource transfer object.

Hyperspectral imaging systems and methods for electronic authentication resource transfers

Aspects of the disclosure are directed to importing software container images, where an image importer that may import a very large number of container images into local repositories from one or more upstream repositories to an enterprise container platform. An associated computing cluster executes containers (for example, applications and operators) based on the imported container images. Each release (version) of a product supported by the enterprise container platform may require importing newer image sets with respect to the current version. With one aspect, an image importer maintains an image list for container images of the current version, where only missing newer container images for a newer version are added to the list. Only the missing container images for the new version are imported to the enterprise container platform. This approach circumvents importing previously imported container and/or available newer images, thus reducing the amount of imported data from upstream repositories.

Incremental image import process for supporting multiple upstream image repositories

Embodiments of the present invention provide a system for generating user identity based encrypted data files using capsule neural networks to prevent identity misappropriation. The system is configured for retrieving at least two images associated with a user from one or more entity databases, generating a consolidated image of the at least two images via an image coupling application, providing the consolidated image to capsule neural networks for training, receiving a real-time image associated with the user, wherein the real-time image is associated with a new application, providing the real-time image to the capsule neural networks, validating the real-time image via the capsule neural network, and determining if the validation is successful to authenticate the user.

System and method for generating user identity based encrypted data files using capsule neural networks to prevent identity misappropriation

Aspects of the disclosure relate to enhancing hybrid traditional neural networks with liquid neural networks for cyber security and offense protection. A computing platform may receive a request to access enterprise organization data. The computing platform may compare the current request to previous requests to determine whether a similar request was previously processed. If a similar request was not previously processed, the computing platform may flag the request as a threat and may analyze the request. The computing platform may extract data from the request and may use the extracted data to generate rules, threat detection algorithms, and training models. The computing platform may use the rules, threat detection algorithms, and training models to train a deep learning neural network to identify and handle threats to an enterprise organization.

Enhancing hybrid traditional neural networks with liquid neural network units for cyber security and offense protection

Aspects of the disclosure relate to transliteration of machine interpretable languages. The computing platform may receive a query, formatted in a first format for execution on a first database. The computing platform may translate the query to a second format for execution on a second database by: 1) extracting non-essential parameters from the query to create a query key; 2) storing the non-essential parameters; 3) executing a lookup function on a query library to identify a translated query corresponding to the query key; 4) based on identifying that the query library includes portions of the query key rather than the query key, recursively identify the translated query by nesting the portions of the query key; and 5) input the non-essential parameters into the translated query to create an output query. The computing platform may execute the output query on the second database.

System and method for recursive transliteration of machine interpretable languages

Systems, computer program products, and methods are described herein for determining data migration using an automated query analyzer tool. The present disclosure is configured to identify at least one input data set associated with at least one application; analyze, by an automated query analyzer tool, the at least one input data set; classify data of the at least one data set as at least one of a standard classification or a non-standard classification; determine at least one metric for the data of the at least one data set; generate a query complexity score for the at least one application; generate an application migration complexity report and an application migration complexity report interface component; and transmit the application migration complexity report interface component to a user device and configure a graphical user interface of the user device with the application migration complexity report interface component.

Growing community of inventors

Little Elm, TX, United States of America

Elvis Nyamwange