Intellectual Property India Publishes Patent Application for 'Intelligent Federated Learning Framework For Secure And Privacy-Preserving AI Applications' Filed by Rapelli Srikanth; Cmr Engineering College; Geethanjali College Of Engineering And Technology; Annamacharya University; and MLR Institute Of Technology

MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641063745 A) filed by Rapelli Srikanth; Cmr Engineering College; Geethanjali College Of Engineering And Technology; Annamacharya University; and MLR Institute Of Technology, Hyderabad, Telangana, on May 20, for 'intelligent federated learning framework for secure and privacy-preserving ai applications.'

Inventor(s) include Mr. Rapelli Srikanth; Dr. C. Anjanamma; V. Sravanthi; Dr. C. V. Lakshmi Narayana; Mr. Oruganti Ramesh; and Ch. Radhika.

The application for the patent was published on May 29, under issue no. 22/2026.

According to the abstract released by the Intellectual Property India: "The Intelligent Federated Learning Framework for Secure and Privacy-Preserving AI Applications presents a distributed artificial intelligence platform designed to enable secure and collaborative AI model training across decentralized environments while preserving data privacy. The framework utilizes federated learning techniques that allow multiple participants, including healthcare institutions, financial organizations, IoT devices, and edge computing systems, to train deep learning models locally without sharing raw data. The system integrates secure aggregation protocols, encrypted communication mechanisms, differential privacy techniques, and intelligent anomaly detection modules to ensure secure and privacy-preserving collaborative learning. The framework supports multiple deep learning architectures including convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and transformer-based models. Communication-efficient optimization methods are incorporated to reduce bandwidth requirements and improve scalability across distributed environments. The proposed invention provides a scalable, secure, and intelligent federated learning solution for privacy-preserving AI applications in healthcare, finance, agriculture, cybersecurity, smart cities, and industrial automation systems."

Disclaimer: Curated by HT Syndication.