International Business Machines Corporation

Accenture Global Services Gmbh

Aniya Aggarwal

Diptikalyan Saha

Pranay Kumar Lohia

Sandeep Hans

Kuntal Dey

Rema Ananthanarayanan

Gagandeep Singh

Samiulla Zakir Hussain Shaikh

Ashish Kundu

Manish Anand Bhide

Sameep Mehta

Shubhashis Sengupta

Roger C Raphael

Mu Qiao

Rajesh M Desai

Danish Contractor

Roshni Ramesh Ramnani

Arjun Natarajan

Anurag Dwarakanath

Joshua F Payne

Varun Parashar

Methods, systems, and computer program products for localization-based test generation for individual fairness testing of AI models are provided herein. A computer-implemented method includes obtaining at least one artificial intelligence model and training data related to the at least one artificial intelligence model; identifying one or more boundary regions associated with the at least one artificial intelligence model based at least in part on results of processing at least a portion of the training data using the at least one artificial model; generating, in accordance with at least one of the one or more identified boundary regions, one or more synthetic data points for inclusion with the training data; and executing one or more fairness tests on the at least one artificial intelligence model using at least a portion of the one or more generated synthetic data points and at least a portion of the training data.

Localization-based test generation for individual fairness testing of artificial intelligence models

Methods, systems, and computer program products for automatically testing AI models in connection with enterprise-related properties are provided herein. A computer-implemented method includes obtaining an artificial intelligence model and information pertaining to one or more existing enterprise-related properties associated with the artificial intelligence model; generating test data for the artificial intelligence model by processing at least a portion of the information pertaining to one or more existing enterprise-related properties; executing at least a portion of the generated test data against the artificial intelligence model; generating, based at least in part on results of the executing of the at least a portion of the generated test data against the artificial intelligence model, one or more enterprise-related property recommendations for the artificial intelligence model; and performing one or more automated actions based at least in part on the one or more enterprise-related property recommendations.

Automatically testing artificial intelligence models in connection with enterprise-related properties

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

Methods, systems, and computer program products for improving trustworthiness of artificial intelligence models in presence of anomalous data are provided herein. A method includes obtaining a machine learning model and a set of training data; determining one or more anomalous data points in said set of training data; for a given one of said anomalous data points, identifying attributes that decrease confidence with respect to at least one output of said machine learning model; determining that a root cause of said decreased confidence corresponds to one of: a class imbalance issue related to said at least one attribute, a confused class issue related to said at least one attribute, a low density issue related to said at least one attribute, and an adversarial issue related to said at least one attribute; and performing step(s) to improve said confidence based at least in part on said determined root cause.

Trustworthiness of artificial intelligence models in presence of anomalous data

Methods, systems and computer program products for automated test case generation are provided herein. A computer-implemented method includes selecting sample input data as a test case for a system under test, executing the test case on the system under test to obtain a result, and applying the result to a local explainer function to obtain at least a portion of a corresponding decision tree. The method further includes determining at least one path constraint from the decision tree, solving the path constraint to obtain a solution, and generating at least one other test case for the system under test based at least in part on the solution of the path constraint. The steps of the method are illustratively repeated in each of one or more additional iterations until at least one designated stopping criterion is met. The resulting test cases form a test suite for testing of a deep neural network (DNN) or other system.

Automated test case generation for deep neural networks and other model-based artificial intelligence systems

Methods, systems, and computer program products for domain aware explainable anomaly and drift detection for multi-variate raw data using a constraint repository are provided herein. A computer-implemented method includes obtaining a set of data and information indicative of a domain of said set of data; obtaining constraints from a domain-indexed constraint repository based on said set of data and said information, wherein the domain-indexed constraint repository comprises a knowledge graph having a plurality of nodes, wherein each node comprises an attribute associated with at least one of a plurality of domains and constraints corresponding to the attribute; detecting anomalies in said set of data based on whether portions of said set of data violate said retrieved constraints; generating an explanation corresponding to each of the anomalies that describe the attributes corresponding to the violated constraints; and outputting an indication of the anomalies and the corresponding explanation.

Domain aware explainable anomaly and drift detection for multi-variate raw data using a constraint repository

Audiovisual documentation of source code in an integrated development environment. A computing device initiates a knowledge transfer session for discussion of source code and generation of audiovisual source code documentation explaining segments of source code from a code base. An audiovisual interface containing a segment of code from the code base is displayed within the integrated development environment. Audio during the knowledge transfer session is recorded with a recording device. Code tracking indicators from an optical tracking device operated by a user are received when the user is reviewing and focused on the segment of code. The computing device determines via the code tracking indicators a module of the segment of code under review. Portions of the recorded audio are associated with the determined module of the segment of code to generate audiovisual source code documentation. The knowledge transfer session is terminated.

Audiovisual source code documentation

A device may obtain text to be analyzed to identify glossary terms. The device may analyze a linguistic unit to generate multiple linguistic units related to the linguistic unit. The device may analyze the multiple linguistic units to generate potential glossary terms. The device may perform a glossary term analysis on the potential glossary terms to generate glossary terms that include a subset of the potential glossary terms. The device may identify included terms that are included in the glossary terms. The device may identify excluded terms that are excluded from the glossary terms. The device may determine a semantic relatedness score between at least one excluded term and at least one included term. The device may selectively add the excluded linguistic term to the glossary terms to form a final set of glossary terms based on the semantic relatedness score, and may output the final set of glossary terms.

Growing community of inventors

New Delhi, India

Aniya Aggarwal