International Business Machines Corporation

Bank of America Corporation

Globalfoundries Inc.

Daedalus Blue LLC

Daedalus Group, LLC

Maharaj Mukherjee

George Albero

Jonathan Lenchner

Shang Qing Guo

Mark Alan Lavin

Utkarsh Raj

Alan Edward Rosenbluth

Kafai Lai

Jinna Zevulun Kim

Gregg M Gallatin

Shlomo Shlafman

Dov Ramm

Emanuel Gofman

Canturk Isci

Carl M Benda

Prashant Thakur

Rahul Gupta

Elvis Nyamwange

Suman Roy Choudhury

Monimala Mukherjee

David B Kumhyr

James A Culp

Manu Jacob Kurian

Shikhar Kwatra

Hari Haranath Madduri

Joanna W Ng

Scott Marshall Mansfield

Andrew Aaron

Deborah Mayers

Benjamin D Moores

Sarbajit Kumar Rakshit

Rhonda L Childress

Gregory J Boss

Jeremy R Fox

Lars W Liebmann

Heather Roseann Dolan

William C Leipold

Daniel Nelson Maynard

Jeffrey Mark Achtermann

Kevin A Delson

Joel W Branch

Elijah Clark

David L DeMaris

Emmanuel Tong-Viet

Arnaud Airy Mathieu

Veerandra S Srivastava

Gandhi Sivakumar

Christopher J Hardee

Siten Sanghvi

Bette L Bergman Reuter

Daniel A Mazzella

Rick A Hamilton, Ii

Lisa Seacat DeLuca

Michael Bender

Eren Kursun

David Bruce Lection

John Maxwell Cohn

Anna Wanda Topol

Brian Paul Gaucher

Faried Abrahams

Naga Vamsi Krishna Akkapeddi

Ioana C Graur

William August Stahlhut

Amol Ashok Dhondse

Morgan Stewart Allen

Anand Pikle

Olga Kocharyan

Kyle A Mayers

John C Nelson

Karen E Davis

Colin Murphy

Vidya Srikanth

Liam S Harpur

Jonathan D Dunne

Kelley Anders

Komminist S Weldemariam

John David Wilson

Mark B Stevens

Jayant R Kalagnanam

Michael Ogrinz

Vijay Kumar Yarabolu

Paul N Krystek

Rama Nand Singh

Farrokh Pourmirzaie

James J Siekman

Lalit Agarwalla

Donald J Samuels

Timothy G Dunham

Lewis William Dewey, Iii

Dustin Paul Stocks

Lloyd Alan Treinish

Rashida A Hodge

Sanjay Arjun Lohar

Chieh-Yu Lin

Rodrigo Alberto Rey

Christopher P Jones

Zachary Baum

Naeem Altaf

Leucir Marin, Jr

John S Murdock, Jr

Aspects of the disclosure relate to energy optimization. A computing platform may receive an event processing request, and may identify its parameters. The computing platform may package, based on the parameters, the event processing request into containers. The computing platform may input the parameters into an energy optimization model, which may identify: a data center computing system and an energy mix for processing the event processing request. The computing platform may encrypt the containers. The computing platform may send, to the data center computing system, the encrypted containers and commands directing the data center computing system to: decrypt the encrypted containers to identify the event processing request, and process the event processing request using the energy mix, which may cause the data center computing system to decrypt the encrypted containers and process the event processing request using the energy mix.

Energy optimization platform using artificial intelligence for container routing

Aspects of the disclosure relate to improving training data used for model generation. The computing platform may receive, from one or more data sources, a labelled data set. The computing platform may apply, to the labelled data set, an unsupervised learning algorithm, which may result in a clustered data set corresponding to the labelled data set. The computing platform may compare, for each data point in the labelled data set, corresponding clustering information and labelling information to identify discrepancies. The computing platform may flag, for data points with identified discrepancies between the corresponding clustering information and labelling information, a data labelling error. Using data points without identified discrepancies between the corresponding clustering information and labelling information, the computing platform may train a supervised learning model. The computing platform then may store the trained supervised learning model.

System and method for ascertaining data labeling accuracy in supervised learning systems

A system is provided for detection and mitigation of unauthorized reproduction of sensitive electronic data. In particular, the system may comprise a networked environment with various computing devices that may be used to store, process, and/or transfer sensitive electronic data. When a user accesses the sensitive data, the contents of the data may be presented as a series of micro dots or pixels. The system may be configured to display rapidly change at least a portion of the micro dots or pixels at a high frequency, such that a snapshot of the sensitive data taken at a singular point in time will not be able to capture all of the data needed to make the data readable to the user. In this way, the system may be able to prevent the unauthorized reproduction of sensitive data within the network environment.

System for detection and mitigation of unauthorized reproduction of sensitive electronic data

Aspects related to an amalgamation platform providing concealed detection of code-passing using steganography are provided. An amalgamation platform may train a scoring engine to generate suspicion scores for code snippets and an amalgamation engine to generate execution scenarios for the code snippets. The platform may embed code in base code of a network using steganography. The platform may use the steganographic code to detect transmission of a code snippet. The platform may generate a suspicion score for the code snippet. The platform may update the scoring engine based on identifying the suspicion score satisfies a threshold. The platform may generate execution scenarios for the code snippet. The platform may determine a match between an execution scenario and a malicious code scenario. The platform may identify the code snippet as malicious and update the amalgamation engine based on the match. The platform may initiate security actions based on the match.

Amalgamation platform providing concealed detection of code-passing using steganography

Apparatus and methods for detecting non-linear data dependencies in machine learning are provided. The methods may include receiving a data set comprising a plurality of data features, the data set for processing by a machine learning model operating on a machine learning system. The methods may also include plotting the data set in multi-dimensional space and linearizing the plotted, multi-dimensional space by feeding the plotted data to an algorithm programmed to execute the Delaunay triangulation method. The methods may further include receiving from the algorithm the data set linearized in a faceted space and detecting linear correlations in the linearized data set. The methods may additional include identifying a first data feature that has a correlation coefficient with a second data feature that is greater than an accuracy metric and removing the first data feature from the data set to create a reduced data set.

Reducing computational burden on machine learning processes by detecting non-linear relationships

Authentication/verification of sub-environments that represent entities within an augmented/virtual reality computing network and virtual objects present in the sub-environment that represent individuals associated with the entity. In response to authentication, a sensory-perceptible indicator (e.g., visual, audible or haptic indicators) is presented to users of the virtual reality computing environment that notify the user that the entity or virtual objects representing the entity have been authenticated. Authentication may be performed via watermarks embedded in images present within the sub-environment, capturing and comparing physical characteristics of an authorized individual representing the entity, cryptographic frequency hopping and/or electromagnetic signatures.

Entity authenticator in augmented or virtual reality computing environments

Systems, computer program products, and methods are described herein for implicit item embedding within a simulated electronic environment. In various embodiments, the invention includes utilizing a hybrid recommendation engine, the invention suggests product placements based on user data and preferences of a specific user. During the initial warm-up period, either user-based or product-based collaborative filtering is applied to assign the user to a collaborative user group until more information about the user becomes available. The hybrid recommendation engine is enhanced through a collaborative clustering component, which involves assigning the user to the collaborative user group via user-based collaborative filtering based on their similar user characteristics, product interests, or product preferences. The invention dynamically alters digital content streamed to the user's device. An implicit product placement module integrates recommended products within the entertainment content, providing a seamless and personalized experience for the user.

System and method for implicit item embedding within a simulated electronic environment

Aspects of the disclosure relate to predicting the spread of malicious software. The computing platform may identify malicious software at a computing device and may input characteristics of the malicious software into a machine learning model to produce time horizons for the malicious software. The computing platform may identify, using a knowledge graph and based on the time horizons, subsets of computing devices, each corresponding to a particular time horizon. The computing platform may perform, at a time within a first time horizon, a first security action for a first subset of computing devices within the first time horizon and a second security action for a second subset of computing devices located within a second time horizon, where the first time horizon and the second time horizon indicate that the first subset will be affected by the malicious software prior to the second subset.

Hybrid machine learning and knowledge graph approach for estimating and mitigating the spread of malicious software

Systems, computer program products, and methods are described herein for automated translation of digital multimedia. The present disclosure is configured to receive, from a user input device, a search request; determine the response for the search query in a first natural language, wherein the response comprises digital multimedia; reconfigure the response for display on the user input device in the preferred natural language, wherein reconfiguring further comprises: determining an intermediate natural language based on a lexical similarity with the preferred natural language; translating, using a first natural language translation subsystem, the response from the first natural language to the intermediate language; and translating, using a second natural language translation subsystem, the response from the intermediate language to the preferred natural language; and display the reconfigured response on the user input device in the preferred natural language.

Natural language generation system for automated translation of digital multimedia

A system is provided for implementing time-restricted access control to electronic digital resources. In some embodiments, the custom set of executable code used to generate the digital resource may provide granular control over access restrictions for accessing, viewing, and/or transferring the digital resource. Such access restrictions may include time duration restrictions, access frequency restrictions, data quality restrictions, and/or the like. In this way, the system may limit access to the digital resource in a secure manner.

System and method for implementing time-restricted access control to electronic digital resources

A computing platform may receive, from a plurality of IoT information sources, historical information associated with a user. The computing platform may generate, based on the historical information, a user specific policy, defining information distribution rules for the user. The computing platform may receive, from an information collection system, a request for information. The computing platform may identify whether or not the request for information requests personal information of the user. Based on identifying that the request for information requests the personal information of the user, the computing platform may identify whether or not the requested personal information violates the user specific policy. Based on identifying that the requested personal information does not violate the user specific policy, the computing platform may obscure the requested personal information, and send, to the information collection system, the obscured personal information.

Permission based information transfer based on internet of things (IoT) insights

Aspects of the disclosure relate to an automated model generation platform for recursive model building. A computing platform may receive a request for automated machine learning model building, and may identify a service offering corresponding to the request. Based on the identified service offering and using machine learning algorithms, the computing platform may select machine learning models and a corresponding sequence of model application (e.g., machine learning model information). The computing platform may store the machine learning model information along with a corresponding indication of the identified service offering. The computing platform may receive a request for model information corresponding to a service access request, and may identify that the service access request corresponds to a problem within the identified service offering. In response, the computing platform may send the machine learning model information, which may cause the enterprise service host system to generate a service output interface.

Automated model generation platform for recursive model building

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 message validation. A computing platform may receive a message, sent by a first device and directed to a second device, from an electronic messaging server. The computing platform may verify, based on message sender details, an identity of a sender of the message. The computing platform may generate, after verifying the identity of the sender of the message, an authentication token for the message, and may inject the authentication token into the message. The computing platform may route, to the electronic messaging server and after injecting the authentication token into the message, the message. The computing platform may receive a request to validate the message, which may include the authentication token and details of the message. The computing platform may identify, using the authentication token and the details of the message, that the message is authenticated.

Email verification using injected tokens for message authentication

User authentication/login occurs prior to a user accessing a network, application, web site/service or coming in contact with a computing device. Pre-authenticating/logging-in of users in advance of the user visiting or accessing the computing technology. A single device passcode that unlocks the device and a passcode vault storing the user's passcodes. Unlocking the passcode vault provides for the passcodes stored therein to be automatically applied to the corresponding entities requiring authentication to grant users access without requiring any user input/actions. Machine-Learning (ML) models that are trained to learn user login patterns are implemented to identify login pattern(s) and subsequently passcodes are retrieved for the entities making up the login pattern(s) from the passcode vault. Prior to the user accessing the entities that make up the login pattern, the present invention accesses the entities and applies the retrieved passcodes to pre-authenticate the user.

Pre-access automated login to computing devices, applications and web sites/services based on machine-learning determined user access patterns

Growing community of inventors

Poughkeepsie, NY, United States of America

Maharaj Mukherjee