Intellectual Property India Publishes Patent Application for 'System For Explainable Federated Learning-Driven Anomaly Detection And Marl Based Adaptive Mitigation In Iot Networks' Filed by Sr University

MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202641001896 A) filed by Sr University, Warangal, Telangana, on Jan. 7, for 'system for explainable federated learning-driven anomaly detection and marl based adaptive mitigation in iot networks.'

Inventor(s) include Arshiya Begum; and Dr. Rupesh Mishra.

The application for the patent was published on Jan. 23, under issue no. 04/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a system (300) for explainable federated learning-driven anomaly detection and multi-agent reinforcement learning-based adaptive mitigation in Internet-of-Things networks. The system (300) includes an IoT device layer (302) having IoT devices (304, 306, 308) configured to collect operational data, an edge node layer (310) having an edge gateway (312), a local anomaly detection module (314) configured to train a local anomaly detection model, and a local explainable artificial intelligence module (316) configured to generate interpretable explanations for detected anomalies. The system (300) further includes a federated coordination layer (318) having a federated server (320), model aggregation unit (322), and global model repository (324). A multi-agent reinforcement learning mitigation layer (326) includes agents (328, 330, 332) configured to receive anomaly alerts and execute mitigation actions. A feedback loop module (334) feeds mitigation outcomes to the local anomaly detection module (314)."

Disclaimer: Curated by HT Syndication.