MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641105467 A) filed by Saveetha Institute Of Medical And Technical Sciences on September 02, 2026, for System And Method For Differntial Privancy Enhanced Federated Learning In Distributed Data Mining Environments.
Inventors include Thanupriya N; Dr. Sheeja Kumari; and Dr Ramya Mohan.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The invention discloses a system and method for integrating differential privacy into federated learning workflowsto enable secure and privacy-preserving distributed data mining. The system allows multiple client devices or_data_holders_to_collaboratively_train_a_machine-leaming-model__ without sharing raw data. Differential privacy noise is applied at the client side, server side, or during gradient aggregation to protect sensitive information from inference, reconstruction, and membership attacks. The method includes adaptive noise calibration based on model sensitivity, local dataset characteristics, and privacy budgets to balance privacy and accuracy. By ensuring that no individual data point significantly influences the global model output, the invention provides robust privacy guarantees while maintaining high utility and scalability in distributed environments such as healthcare, finance, IoT systems, and enterprise data analytics.
Disclaimer: Curated by HT Syndication.
