Bank of America Corporation

Sakshi Bakshi

Siva Kumar Paini

Durga Prasad Kutthumolu

Sudhakar Balu

Srinivasa Jitendra Dhanwada

Sathya Thamilarasan

Nagalaxmi Sama

Shyamala Manoharan

Sri Lakshmi Priya Doraiswamy

Amod Jha

Sneha Padiyar

Shilpi Choudhari

Sreekanth Raghuveer Maringanti

Kapil Juneja

Ramaswamy M

Saravanan Balasubramanian

Pushkar Taneja

Saravana Kumar Pd

Manikandan Rajaraman

Ashlesha Mithra

Saurabh Rajpal

Hwee Leng Toh

Keerthivasan Kulasekaran

Himanshi Sharma

Rajesh Kancharla

Sharat Chandran

Arif Ahmad Khan

Arvind Bansal

Ramakanth Bachu

Ankit Kumar

Jayakumar Manokaran

Amit Kumar Sati

Sri Doraiswamy

Subhasree Baskaran

A real-time payment security method and system for preventing eavesdropping attacks on computing devices may include a plurality of sensors configured to detect anomaly-type behavior indicative of a security threat. The plurality of sensors may be configured to share data, and may be configured to eliminate false-positive anomaly-type behavior indicative of a security threat. The system and method may further include a hash chain network comprising a plurality of hash nodes, and a dynamic authentication mapper, wherein the dynamic authentication mapper may be powered by a cognitive artificial intelligence (AI) engine, and wherein the dynamic authentication mapper may be configured to generate a user notification of valid anomaly-type behavior indicative of a security threat thereby preventing an eavesdropping attack.

Intelligent method and apparatus for secure payment transaction leveraging environment sensing real-time smart hash chain sensors

A system for updating a software code executes a current version of the software code on a web application. The system receives a request message to update the current version of the software code to a new version of the software code. The system determines whether the software code is still being executed on the web application. In response to determining that the software code is still being executed on the web application, the system identifies a subset of portions of the software code that have not yet been executed, executes an update instruction to cause the subset of portions of the software code to be updated, and moves the updated subset of portions of the software code from a first memory block to a second memory block.

System and method for dynamic switching between an old version and a new version of a software code

Aspects of the disclosure relate to a distributed evaluation platform. The distributed evaluation platform may train a machine learning model based on historical nonfungible tokens. The distributed evaluation platform may receive client information from a client device. The distributed evaluation platform may generate NFTs corresponding to the client information. The distributed evaluation platform may generate soft tokens corresponding to each NFT. The distributed evaluation platform may apply test cases to the soft tokens. The distributed evaluation platform may generate remedial tokens based on the soft tokens and remediation actions. The distributed evaluation platform may apply the test cases to the remedial tokens. The distributed evaluation platform may overwrite the NFTs using the remedial tokens. The distributed evaluation platform may send an event processing request to an event processing system. The distributed evaluation platform may refine the machine learning model based on the NFTs.

Distributed evaluation platform for nonfungible tokens using virtual token cloning

Arrangements for an intelligent monitoring platform using a cybersecurity mesh and graph neural networks (GNNs) are provided. A platform may train multiple machine learning models (e.g., a GNN model, a cybersecurity engine, and a monitoring model). The platform may generate, using a GNN model, a suspicion score for a received event processing request. Based on determining the suspicion score satisfies a threshold, the platform may generate a threat score using a cybersecurity engine. The platform may generate an anomaly record for the event processing request based on the threat score and using a monitoring model. The platform may determine a preferred node of a cybersecurity mesh for routing the event processing request based on the anomaly record. The platform may determine a threat prevention response based on the preferred node. The platform may initiate one or more security actions based on the threat prevention response.

Intelligent monitoring platform using graph neural networks with a cybersecurity mesh and associated cybersecurity applications

A system for classifying software code determines a first function, a first set of operations, and a first criticality level of a first software code. The system determines a second function, a second set of operations, and a second criticality level of the second software code. The system determines that the first function of the first software code corresponds to the second function of the second software code. The system compares the operations of the first software code with the operations of the second software code and determines that the first and second software code have at least one operation in common with each other. The system determines that the first criticality level of the first software code corresponds to the second criticality level of the second software code. In response, the system classifies the first software code and the second software code in a first group.

System and method for classifying software code based on functionality and criticality

Aspects of the disclosure relate to upgrading an application within a simulated version of an enterprise system to detect and correct potential errors as a result of the upgrade. A computing platform may create a simulated version of the enterprise system by receiving metadata associated with the enterprise system, and converting the metadata into system parameters. Virtual parameters may be created by the computing system based on upgrading an application within the simulated version of the enterprise system. The computing system may determine errors caused by the application upgrade within the simulated version of the enterprise system based on differences between the system parameters and the virtual parameters. The computing platform may determine actions to correct the errors and input the results and feedback into an AI engine to further refine the accuracy and reliability of the computing platform over time.

Artificial intelligence (AI) supported graph enabled method to manage upgrades for applications

Methods and systems described herein for addressing issues associated with varying graph analytics tools that require different tool-specific coding languages. An artificial intelligence (AI) sub-system of various modules extracts metadata from a dataset and identifies nodes and relationships in the dataset using the metadata. The dataset is matched with a corresponding graph-analytics template in a data store, and a dynamic template modifier modifies the corresponding graph-analytics template. In some examples, the AI system generates smart guided videos with logical breakpoints that are embedded along with templates for quick learning and to build faster graphical analytics. The AI system includes a dynamic template modifier and a cognitive smart AI engine that includes a graph.

Method for dynamic AI supported graph-analytics self learning templates

A system for protecting non-public information from a malicious user determines a set of input data entered into a web application. The system determines whether each input data is associated with non-public information. In this process, the system compares each input data with each of a set of keywords that are known to be associated with non-public information. In response to determining that input data corresponds to a keyword, the system determines that the input data comprises non-public information. In response, the system masks the input data and tags an authentication instruction to the masked input data. The system may receive a request to unmask the masked input data. In response to receiving the request, the system executes the authentication instruction.

System and method for protecting non-public information from malicious users

Aspects of the disclosure relate to a dual-system reconciliation process of trades. A first real-time trade processing and centralized reconciliation engine may continuously process trades in real-time and may perform centralized reconciliation of the trades. An anomaly detection and reconciliation mesh analysis engine may tokenize trade metadata received from the first real-time trade processing and centralized reconciliation engine, generate tokenized trade digital DNA, generate hashed tokenized trade digital DNA, evaluate and validate the hashed data, and perform decentralized reconciliation mesh analysis of the hashed data using a reconciliation mesh. The anomaly detection and reconciliation mesh analysis engine may send one or more monitory policies from the reconciliation mesh to a user device and may receive a first monitory policy selection from the user device. The anomaly detection and reconciliation mesh analysis engine may update the decentralized reconciliation mesh based on the first monitory policy selection.

System and method for transaction reconciliation and anomaly detection using tokenized decentralized mesh

Systems, computer program products, and methods are described herein for implementing parametric optimization analysis for resource selection. The present invention is configured to determine a first set of requirements associated with a resource exchange agreement; identify one or more non-fungible tokens (NFTs) for one or more categories of past resource exchange agreements based on at least the first set of requirements; extract, from the one or more NFTs, one or more resource descriptors associated with one or more past resource exchange agreements in the one or more categories; predict, using a machine learning subsystem, an optimal resource valuation model for one or more resources that meet the first set of requirements using the one or more resource descriptors and the first set of requirements; and transmit control signals configured to cause a first end-point device to display the optimal resource valuation model.

System for implementing parametric optimization analysis for resource selection

Aspects of the disclosure relate to monitoring, evaluating, and repairing bots in a hashchain-based distributed bot hub that process a workflow. In some embodiments, a computing platform may receive workflow information associated with performing a first workflow that includes executing one or more tasks using a plurality of virtual bots, instantiate a first subset of the plurality of bots to process the one or more tasks of the first workflow, and instantiate a first subset of the plurality of bots to process the one or more tasks of the first workflow. identifying a potential anomalous activity may include causing the monitor bot hub to remove the identified bot to a quarantine hub, and execute a repair process on the identified bot in the quarantine hub.

Dynamic workflow engine in an enterprise bot hub system

A system for detecting and countering malicious code executed on a web application detects a set of configuration parameter values from the web application. The system compares each configuration parameter value with a counterpart from among a set of historical configuration parameter values. The system determines the difference between a configuration parameter with a counterpart historical configuration parameter values. If the system determines that the difference between the configuration parameter and the counterpart historical configuration parameter is more than a threshold rate, the system determines that a malicious code is executed on the web application. In response, the system determines a function associated with the malicious code. The system determines one or more actions to counter the malicious code based on the function of the malicious code. The system executes at least one of the one or more actions.

System and method for detecting and countering malicious code

A system includes a plurality of computing nodes that form a blockchain network, wherein one or more of the computing nodes is a metaverse computing node configured to generate a mixed reality environment. A processor of at least one computing node is configured to receive information relating to a suspicious data interaction associated with a data file of a user, simulate, based on the received information, the suspicious data interaction in a synthetic mixed reality environment that is substantially identical to the mixed reality environment, verify the suspicious data interaction while the simulated data interaction is being performed, when the suspicious data interaction cannot be verified, disable one or more future data interactions processed using the same smart contract used to process the suspicious data interaction, and when the suspicious data interaction is successfully verified, terminate the simulated data interaction and process the suspicious data interaction.

Securing data in a metaverse environment using simulated data interactions

Aspects of the disclosure relate to generating synthetic invisible fingerprints for metadata security and document verification using generative artificial intelligence (AI). A computing platform may capture first fingerprint information via a computing device. The first fingerprint information may include one or more physical fingerprint images of a user. The computing platform may encode the first fingerprint information in accordance with a quantum key distribution scheme. The computing platform may store the encoded first fingerprint information in a data store. Based on the encoded first fingerprint information and using a generative artificial intelligence algorithm, the computing platform may generate second fingerprint information. The second fingerprint information may include one or more synthetic fingerprint images associated with the one or more physical fingerprint images of a user. The computing platform may transmit the second fingerprint information for smart contract generation.

Growing community of inventors

New Delhi, India

Sakshi Bakshi