International Business Machines Corporation

Bank of America Corporation

Globalfoundries Inc.

Daedalus Blue LLC

Maharaj Mukherjee

Jonathan Lenchner

George Albero

Shang Qing Guo

Mark Alan Lavin

Alan Edward Rosenbluth

Utkarsh Raj

Kafai Lai

Gregg M Gallatin

Shlomo Shlafman

Dov Ramm

Emanuel Gofman

Canturk Isci

Rahul Gupta

Jinna Zevulun Kim

Elvis Nyamwange

Carl M Benda

Monimala Mukherjee

Suman Roy Choudhury

David B Kumhyr

James A Culp

Prashant Thakur

Manu Jacob Kurian

Shikhar Kwatra

Hari Haranath Madduri

Joanna W Ng

Scott Marshall Mansfield

Andrew Aaron

Deborah Mayers

Sarbajit Kumar Rakshit

Rhonda L Childress

Benjamin D Moores

Gregory J Boss

Jeremy R Fox

Lars W Liebmann

William C Leipold

Daniel Nelson Maynard

Heather Roseann Dolan

Jeffrey Mark Achtermann

Kevin A Delson

Joel W Branch

David L DeMaris

Emmanuel Tong-Viet

Arnaud Airy Mathieu

Veerandra S Srivastava

Gandhi Sivakumar

Christopher J Hardee

Siten Sanghvi

Elijah Clark

Bette L Bergman Reuter

Daniel A Mazzella

Michael P Robertson

Rick A Hamilton, Ii

Lisa Seacat DeLuca

Michael Bender

David Bruce Lection

Eren Kursun

John Maxwell Cohn

Anna Wanda Topol

Brian Paul Gaucher

Faried Abrahams

Ioana C Graur

Naga Vamsi Krishna Akkapeddi

William August Stahlhut

Amol Ashok Dhondse

Morgan Stewart Allen

Anand Pikle

Kyle A Mayers

John C Nelson

Liam S Harpur

Jonathan D Dunne

Kelley Anders

Komminist S Weldemariam

John David Wilson

Mark B Stevens

Michael Ogrinz

Jayant R Kalagnanam

Paul N Krystek

Vijay Kumar Yarabolu

Rama Nand Singh

Farrokh Pourmirzaie

Lalit Agarwalla

Donald J Samuels

Timothy G Dunham

Lewis William Dewey, Iii

Olga Kocharyan

Lloyd Alan Treinish

Rashida A Hodge

Sanjay Arjun Lohar

Chieh-Yu Lin

Rodrigo Alberto Rey

Christopher P Jones

Zachary Baum

Karen E Davis

Naeem Altaf

Leucir Marin, Jr

John S Murdock, Jr

Colin Murphy

Kanad Chakraborty

Leucir Marin Junior

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

Alternative distribution/communication of and access to One-Time Passwords/Passcodes (OTPs). Triggering events are detected that result in the OTP being communicated to a communication device different from the device designated by the user for receiving OTPs. The triggering event may be determination that the user's designated device (i) is not currently in possession of the user, (ii) is located in a geo-location designated for No-OTP receipt, and/or (iii) is currently in an inoperable state. The different communication device may be a device other than one in possession/control of the user and may be a device designated by the user or the device may be one selected, based on proximity of location to the user, from a network of trusted devices/individuals.

Alternative distribution and accessing of one-time passwords (OTPs)

A computing platform may train, using historical call information, a prompt generation model to identify, for an initiated call between a first individual and a second individual, one or more security prompts to validate an identity of the first individual. The computing platform may detect and temporarily pause a call. The computing platform may input, into the prompt generation model, information of the call, which may cause the prompt generation model to output the security prompts, which may be customized CAPTCHA tests based on the information. The computing platform may send, while the call is paused and to a user device of the first individual, the security prompts. The computing platform may receive, while the call is paused and from the user device, responses to the one or more security prompts. The computing platform may validate, while the call is paused, the responses, and resume the call.

Automated vishing detection to prevent deepfake and chatbot attacks

Aspects of the disclosure relate to energy optimization. A computing platform may receive a cryptocurrency request indicating a gas price and KPIs of the cryptocurrency request. The computing platform may input the gas price and the KPIs into a mining optimization model, which may cause the mining optimization model to output an energy mix for use in processing the cryptocurrency request. The energy mix may indicate energy sources, capable of providing an amount of energy needed to process the cryptocurrency request and used to support operation of a data center configured to process cryptocurrency requests, and a cost of the amount of energy from the energy mix may be less than a cost of the amount of energy from other available energy sources. The computing platform may send commands directing the data center to process the cryptocurrency request using the energy mix, which may cause it to do so.

Energy optimization platform for cryptocurrency mining

Aspects of the disclosure relate to machine learning and quantum computing. A computing platform may receive historical information, which may include feature information and rate of change information. The computing platform may train, a ML model, by inputting the feature information and the rate of change information, which may make the ML model stable against data drift. The computing platform may receive a first query, input the first query into the ML model, to identify a solution to the first query, which may include identifying a first solution, perturbing the first solution a number of times, and ultimately identifying a second solution, more accurate than the first solution. The computing platform may send this second solution to the user device.

Model optimization and stabilization using quantum computing

Systems, computer program products, and methods are described herein for enhanced encryption orchestration and application integration frameworks. The system performs steps of initializing a broker application to act as a data security broker within a computing environment; providing an application programming interface (API) for external application interaction; receiving and processing requests via the API for access to encrypted code and data; containerizing the code and data within an isolated environment, subject to predefined rules; monitoring usage to ensure adherence to these rules; initiating self-destruction of the container upon reaching a predetermined usage limit or condition; and securely erasing all sensitive data and code after usage completion.

System and method for enhanced encryption orchestration and application integration framework

A device for performing a secured operation is disclosed. The device is embedded with a predefined data item and verification information. The verification information is uniquely associated with the user of the device. The verification information is linked to the identity of the user. The verification information is configured to be extracted in conjunction with the secured operation being performed. The secured operation is performed in response to the verification information being verified. A system and method for performing the secured operation are also disclosed.

System, device, and method for performing secured operations

Methods for detecting non-linear data dependencies in machine learning using hybrid quantum computing. Methods include receiving a selection of an accuracy metric. Methods include receiving a data set comprising a plurality of data elements for processing by a machine learning model operating on a machine learning system. Methods include identifying a plurality of data elements within each data set. Methods include identifying one or more features for each data element. Methods include determining a total number of features for the data set. Methods include reducing, by a quantum annealing method, based on the accuracy metric, the total number of features to a reduced number of features. Methods include inputting the reduced number of features into the machine learning model. Methods include outputting a result from the machine learning model.

Non-linear data dependency detection in machine learning using hybrid quantum computing

A computing device may configure a plurality of device partitions. The computing device may send, to a one time password (OTP) server and via an interface of a first partition of the plurality of device partitions, a login request. The computing device may receive, at a second partition of the plurality of device partitions, an OTP. The computing device may access, by validating authentication credentials corresponding to the second partition of the plurality of device partitions, the OTP. The computing device may send, to the OTP server, the OTP. The computing device may access, upon receiving confirmation of validation of the OTP, services hosted by the OTP server.

Enhanced security with multiple factor authentication at devices using partitions

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

A computing platform may train an image comparison model to predict system failure for technology infrastructure based on telemetry state images. The computing platform may receive telemetry data for the plurality of computing systems over a period of time. The computing platform may generate, based on the telemetry data and for each parameter represented in the telemetry data, a telemetry state image, where each telemetry state image plots the period of time on an x axis, plots the plurality of computing systems on a y axis, and is specific to a respective parameter represented in the telemetry data. The computing platform may classify, using the image comparison model and using parallel processing, the telemetry state images. The computing platform may identify a likelihood of failure for the technology infrastructure, and may cause modification of operations at one or more of the plurality of computing systems to prevent a predicted failure.

System and method for matching multiple featureless images across a time series for outage prediction and prevention

Arrangements for continuous authentication and secure access control are provided. In some aspects, a computing platform may receive user data from a plurality of user data sources. The user data may include a plurality of different data types. The computing platform may use the user data to train a machine learning model, which may then be used to generate user specific baseline data. Subsequent user data may be received and analyzed, using the machine learning model, to determine whether an anomaly exists between the subsequent user data and the baseline data. If not, the user may be considered authenticated and second user data may be received and analyzed to continuously authenticate the user. If an anomaly is detected, the anomalous data and other data may be further analyzed to determine whether to authenticate the user or execute a response action.

Multi-computer system for providing continuous authentication and secure access control

Aspects of the disclosure relate to energy optimization. A computing platform may receive an event processing request. The computing platform may identify parameters of the event processing request. The computing platform may input the parameters into a global energy optimization model, to identify an edge computing system at which to process the event processing request. The computing platform may route the event processing request to the edge computing system along with commands to process the event processing request using an energy mix identified by a local energy optimization model, corresponding to the edge computing system, which may cause the edge computing system to: input the parameters of the event processing request into the local energy optimization model to identify the energy mix, and process, using the energy mix, the event processing request.

Energy optimization platform using artificial intelligence and edge computing

Systems, computer program products, and methods are described herein for data protection in a distributed network via reconstruction and analysis of data segments. The present invention is configured to initiate a network flow analysis to assign indicators to specialized access nodes of a network diagram, execute a first cut to remove predetermined nodes, store the corresponding discrete data segments for each of the first plurality of electronic communications at the nodes, construct a first arrangement of a selected group of the corresponding discrete data segments, determine a presence of sensitive information, and construct additional arrangements of the selected group of the corresponding discrete data segments to determine a presence of sensitive information.

System and method for data protection in a distributed network via reconstruction and analysis of data segments

Aspects of the disclosure relate to transliteration of machine interpretable languages. A computing platform may generate a plurality of query keys, configured for use in translating queries from a first format to a second format, which may include, for each input query corresponding to the plurality of query keys: selecting, based on features of the input query, a compaction method, and applying the selected compaction method to the input query to produce a corresponding query key. The computing platform may store the plurality of query keys in a lookup table. The computing platform may receive a first query, corresponding to the input queries, formatted in the first format. The computing platform may translate, by identifying a query key corresponding to the first query in the lookup table, the first query to produce a second query, formatted in the second format. The computing platform may execute the second query.

Transliteration of machine interpretable languages for enhanced compaction

Growing community of inventors

Poughkeepsie, NY, United States of America

Maharaj Mukherjee