Intellectual Property India Publishes Patent Application for A System And Method For Federated Learning-Based Secure Artificial Intelligence Training And Distributed Data Processing

MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641078256 A) filed by Vardhaman College Of Engineering on June 25, 2026, for A System And Method For Federated Learning-Based Secure Artificial Intelligence Training And Distributed Data Processing.

Inventors include Mrs. Yadla Sunanda; Mr. S Ranjith Reddy; Dr. Lingam Sunitha; Dr. Mannava Yesubabu; Ms. Dhanalaxmi Chinthala; and Mr. Vinayak.

The application for the patent was published on July 03, 2026, under issue no. 27/2026.

Abstract: ABSTRACT A System and Method for Federated Learning-Based Secure Artificial Intelligence Training and Distributed Data Processing The present disclosure relates to a system and method for federated learning based secure artificial intelligence training and distributed data processing. The system allows the collaborative training of artificial intelligence models in multiple distributed computing nodes with data privacy as local datasets are maintained at respective nodes. The disclosed system comprises an adaptive trust scoring and node reputation engine to evaluate participant reliability, an intelligent model fragmentation module to generate encrypted model fragments, a quantum-resistant secure communication module to securely transmit, and a blockchain-assisted verifiable aggregation module to validate integrity in a decentralized manner. The system further comprises a federated model poisoning detection engine, a digital twin based learning validation module, a homomorphic privacy preservation module and a self evolving aggregation optimization module configured to dynamically optimize aggregation strategies. Communication optimization, risk prediction, and energy-aware participation mechanisms further boost scalability and efficiency. The invention disclosed herein provides a secure, adaptive, and technically advanced federated artificial intelligence infrastructure to enhance cybersecurity, privacy preservation, communication efficiency, model reliability, and distributed learning performance.

Disclaimer: Curated by HT Syndication.