International Business Machines Corporation

Kyndryl, Inc.

Mu Qiao

Ramani Ranjan Routray

Divyesh Jadav

Sunhwan Lee

James E Olson

Rakesh Jain

Roger C Raphael

John Jason Auvenshine

Stanley C Wood

Luis Angel D Bathen

Gabor Madl

Rajesh M Desai

Yuya Jeremy Ong

Eric Kevin Butler

Bernhard Julius Klingenberg

Dylan J Fitzpatrick

Heiko Hary Ludwig

Taiga Nakamura

Luis Angel Bathen

Quan Zhang

Simon-Pierre Genot

Jeremy R Fox

Martin G Keen

Ashish Kundu

Yang Song

Nagapramod S Mandagere

Scott Schumacher

Rama Kalyani T Akkiraju

Shun Jiang

Berthold Reinwald

Hovey Raymond Strong

Claudio Santos Pinhanez

Nikolaos Anerousis

Debdoot Mukherjee

Prithviraj Sen

Peifeng Yin

Arjun Natarajan

Mohamed Mohamed

Hamid Reza Motahari Nezhad

Marisa Affonso Vasconcelos

Shubhi Asthana

Samir Tata

Rogerio Abreu De Paula

Aniya Aggarwal

Joshua F Payne

German H Flores

Daniela Trevisan

Nicholas Linck

Angineh Aghakiant

Abhinandan Kelgere Ramesh

Mikael H Lindström

Hogun Park

Claire Abu-Assal

Alan C Skinner

Tongtong Liu

Wenqi Wei

Obinna B Anya

Sushama Karumanchi

Hyun-Woo Kim

Alex R Martin

Preethi Anantharaman

Nishtha Atrey

Meenakshi Madugula

Archana Yadawa

Bailey Duncan

Mechanisms are provided for detecting adversarial attacks on graph data structures. A first graph fingerprint engine generates, for a first graph data structure, a first fingerprint data structure-based on features extracted from the first graph data structure. A second graph data structure is received, and a second graph fingerprint engine generates a second graph fingerprint data structure based on features extracted from the second graph data structure. An adversarial attack detection engine compares the first fingerprint data structure to the second fingerprint data structure to determine whether the first fingerprint data structure matches the second fingerprint data structure. In response to the first fingerprint data structure not matching the second fingerprint data structure, the adversarial attack detection engine outputs an output indicating that the second data structure corresponds to an adversarial attack.

Fingerprint based graph adversarial defense

A context aware code snippet recommendation method, system, and computer program product that includes generating comments for source code, learning semantically meaningful sentence embeddings based on the comments, and retrieving code snippets from the source code based on the learned semantically meaningful sentence embeddings.

Context aware code snippet recommendation

A processor can be configured to receive data associated with, and/or access to, a computing system's file system structure. The processor can also be configured to determine file patterns, file path patterns and/or graph patterns associated with the computing system. The processor can also be configured to build a graph structure having nodes and edges, the graph structure representing the file patterns, file path patterns and graph patterns, wherein the nodes of the graph structure represent files and attributes of the files and the edges of the graph structure represent connectivity between the files. The processor can also be configured to train, based on the graph structure, a first machine learning model to learn a feature vector associated with a file. The processor can also be configured to train, based on the feature vector, a second machine learning model to identify a vulnerable ransomware target.

Machine learning based vulnerable target identification in ransomware attack

Systems and techniques that facilitate empathetic or emotional query response are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory that can execute the computer executable components stored in memory. The computer executable components can comprise a first machine learning model that generates a first response portion, wherein the first response portion comprises a technical response to the input query, and a second machine learning model that generates a second response portion, wherein the second response portion comprises an empathetic or emotional response to the emotion portion of the input query.

Empathetic query response using mixture of experts

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations that include analyzing interactions by a user within a network and generating a user profile for the user. The operations by the processor may further include identifying an attempt by the user to share a post via the network and prompting the user with a personalized alert to evaluate the post, wherein the personalized alert is generated based on the interactions, the user profile, and the properties of the post.

Personalized alert generation based on information dissemination

A method, computer program product, and computer system are provided. A processor receives message data from a natural language conversation among participants in a project. A processor identifies at least two tasks mentioned in the message data. A processor determines a dependency between the at least two tasks based on the output of a sequential language model, where the messages associated with the at least two tasks are inputs to the sequential language model. A processor generates a directed graph depicting the at least two tasks and the determined dependency of the at least two tasks. A processor shares a directed graph across participants. A processor notifies participants who are blocked when dependent tasks are complete.

Task dependency extraction sharing and notification

A computer-implemented method is provided for predicting future data values or target labels of multivariate time series data. The method includes receiving the multivariate time series data having present values, systematic missing values, and random missing values. The method further includes masking the present values, the systematic missing values, and the random missing values using triplet encodings. The method also includes determining time intervals between current missing values, from among the systematic missing values and the random missing values, and immediately preceding ones of the present values. The method additionally includes training, by a computing device, at least one recurrent neural network with the triplet encodings, the time intervals, and multivariate time series data to perform a feedforward pass on the recurrent neural network predicting the future data values or the target labels. A forward imputation is utilized by the computing device to impute any of the current missing values.

Predicting multivariate time series with systematic and random missing values

A processor distributes, from a server, a trained supervised machine learning (ML) model and supervised and unsupervised feature information to a plurality of client devices; at each client device, trains the supervised ML model using local data to generate a local supervised ML model, constructs a local unsupervised ML model using the unsupervised feature information, and deploys the local supervised and unsupervised ML models; determining when a detection performance difference between the local supervised and unsupervised ML models reaches a threshold; identifies a proposed change to the supervised or unsupervised feature information; deploys the proposed change on one client device; responsive to determining the proposed change improves the detection performance of that client device, communicates the proposed change to a sampled set of client devices; and responsive to determining the proposed change improves the detection performance of a majority of the sampled set, communicates the proposed change to the server.

Dynamically federated data breach detection

An apparatus includes a cable having two ends and at least two object markers coupled to the cable configured to enable augmented reality (AR) detection of each end of the cable among a plurality of cables. A computer-implemented method using augmented reality (AR) technology includes selecting a cable of interest and identifying an object marker positioned toward a first end of the cable of interest. The method also includes storing the object marker, scanning a plurality of cables, and identifying a second end of the cable of interest based an instance of the object marker positioned toward the second end of the cable of interest. A computer program product for detecting ends of cables using augmented reality (AR) technology includes a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a computer to cause the computer to perform the foregoing method.

Identifying cable ends using augmented reality

Techniques for data integration and labeling are provided. Training real-world signal data is collected for a physical environment, where the training real-world signal data comprises at least one of (i) coordinate information or (ii) a direction to move. Simulated signal data is generated for a first portion of the physical environment, and an aggregate data set is generated comprising the training real-world signal data and the simulated signal data. A machine learning (ML) model is trained using the aggregate data set. A first real-world data point is received, where the first real-world data point does not include coordinate information, and the first real-world data point is labeled based at least in part on coordinate information of the aggregate data set.

Integrating simulated and real-world data to improve machine learning models

A computer-implemented method according to one embodiment includes receiving historical two-dimensional (2D) multivariate time series data; transforming the historical 2D multivariate time series data into a three-dimensional (3D) temporal tensor; training one or more deep volumetric 3D convolutional neural networks (CNNs), utilizing the 3D temporal tensor; and predicting future values for additional multivariate time series data, utilizing the one or more trained deep volumetric 3D CNNs.

Performing multivariate time series prediction with three-dimensional transformations

Preserving distributions of data values of a data asset in a data anonymization operation is provided. Anonymizing data values is performed by transforming sensitive data in a set of columns over rows of the data asset while preserving distribution of the data values in the set of transformed columns to a defined degree using a set of autoencoders and loss function. The autoencoders are base trained from preexisting data in a data assets catalog and actively trained during data dissemination. Parametric coefficients of the loss function are configured and the threshold is generated using policies from an enforcement decision for the data asset and data consumer. The loss function value of a selected row is compared to the threshold. Transformed data values of the selected row are transcribed to an output row when the loss function value is greater than the threshold and disseminated to the data consumer.

Learning to transform sensitive data with variable distribution preservation

Systems and methods are described for a data breach detection based on snapshot analytics. The described systems and methods identify a plurality of snapshots of a data structure, identify a plurality of leaf nodes of the data structure for each of the snapshots, generate a vector of data attributes for each of the leaf nodes, assign a weight to each of the vectors to produce a set of weighted vectors for each of the snapshots, compute a distance metric between each pair of the snapshots based on the corresponding sets of weighted vectors, and detect an abnormal snapshot among the plurality of snapshots based on the distance metrics.

Data breach detection

Provided is a method, computer program product, and system for automatically predicting unknown semantic data types in a rectangular dataset using a holistic knowledge of said dataset. A processor may receive one or more rectangular datasets, the one or more rectangular datasets comprising a plurality of columns having a set of known semantic data types. The processor may extract a set of features from the plurality of columns, where the set of features is used to determine a relationship among each column of the plurality of columns. The processor may construct a set of training data based on the extracted set of features. Using the training data, the processor may train a machine learning model to predict a semantic data type of a target column in a rectangular dataset having an unknown semantic data type.

Semantic data type classification in rectangular datasets

Data protection activity time in a backup environment can be predicted with a computer-implemented method. The method includes gathering datasets of data points from a range of backup components of a backup system and constructing input features for a predictive machine learning model, where the input features relate to backup parameters of the backup system. The method also includes training the predictive machine learning model to predict data protection activity times for the backup system by using the gathered datasets and applying the input features to the model. The method also includes deploying the trained predictive machine learning model to predict a data protection activity time of a backup system formed of a set of the backup components.

Prediction of a data protection activity time for a backup environment

Growing community of inventors

Belmont, CA, United States of America

Mu Qiao