Intellectual Property India Publishes Patent Application for Federated Learning-Based Privacy-Preserving System For Distributed Iot Device Intelligence

MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641101925 A) filed by Sri Venkateswara College Of Engineering Autonomous; R Nandhakumar, Assistant Professor, Department Of Ece, Sv College Of Engineering; K Kartheek, Assistant Professor, Department Of Ece, Sv College Of Engineering; D Srilatha, Assistant Professor, Department Of Ece, Sv College Of Engineering; M. Bala Murali Krishna, Assistant Professor, Department Of Ece, Sv College Of Engineering; P. Bharathi, Assistant Professor, Department Of Ece, Sv College Of Engineering; V. Umadevi, Assistant Professor, Department Of Ece, Sv College Of Engineering; Varalakshmi Omkaram, Lab Technician, Department Of Ece, Sv College Of Engineering; L. Mahesh,; Assistant Professor, Department Of Ece, Sv College Of Engineering; Chimakurthy Sreelakshmi, Assistant Professor, Department Of Ece, Sv College Of; G Naveenkumar, Assistant Professor, Department Of Ece, Sv College Of Engineering; Dr. S Salma, Assistant Professor, Department Of Ece, Sv College Of Engineering; and Venkata Lakshmi Keerthi K, Assistant Professor, Department Of Ece, Sv College Of on August 24, 2026, for Federated Learning-Based Privacy-Preserving System For Distributed Iot Device Intelligence.

Inventors include Sri Venkateswara College Of Engineering Autonomous; R Nandhakumar, Assistant Professor, Department Of Ece, Sv College Of; K Kartheek, Assistant Professor, Department Of Ece, Sv College Of Engineering; D Srilatha, Assistant Professor, Department Of Ece, Sv College Of Engineering; M. Bala Murali Krishna, Assistant Professor, Department Of Ece, Sv College Of; P. Bharathi, Assistant Professor, Department Of Ece, Sv College Of Engineering; V. Umadevi, Assistant Professor, Department Of Ece, Sv College Of Engineering; Varalakshmi Omkaram, Lab Technician, Department Of Ece, Sv College Of Engineering; L. Mahesh,; Assistant Professor, Department Of Ece, Sv College Of Engineering; Chimakurthy Sreelakshmi, Assistant Professor, Department Of Ece, Sv College Of Engineering; G Naveenkumar, Assistant Professor, Department Of Ece, Sv College Of Engineering; Dr. S Salma, Assistant Professor, Department Of Ece, Sv College Of Engineering; and Venkata Lakshmi Keerthi K, Assistant Professor, Department Of Ece, Sv College Of Engineering.

The application for the patent was published on August 28, 2026, under issue no. 35/2026.

Abstract: A Federated Learning-Based Privacy-Preserving System for Distributed IoT Device Intelligence is disclosed. The system comprises distributed IoT devices, edge intelligence nodes, a federated learning coordinator, a privacy-preservation engine, secure aggregation modules, blockchain-assisted verification mechanisms, and cloud analytics infrastructure. The invention enables collaborative machine-learning model training without transmitting raw data from participating devices. Adaptive differential privacy, homomorphic encryption, secure aggregation, and trust- based validation mechanisms ensure confidentiality, integrity, and scalability. The system supports real-time distributed intelligence for smart manufacturing, healthcare, agriculture, transportation, industrial IoT, and smart city applications while significantly reducing privacy risks, communication overhead, and cybersecurity vulnerabilities. The rapid proliferation of Internet of Things (IoT) devices has generated unprecedented volumes of data at the network edge. Traditional centralized machine learning approaches require transmitting sensitive data from IoT devices to cloud servers, leading to privacy concerns, communication overhead, and regulatory challenges. Federated Learning (FL) has emerged as a promising paradigm that enables collaborative model training without sharing raw data. This paper proposes a Federated Learning-Based Privacy-Preserving System for Distributed IoT Device Intelligence that facilitates secure, scalable, and efficient machine learning across heterogeneous IoT environments. The proposed framework integrates federated learning, differential privacy, secure aggregation, and edge intelligence to preserve data confidentiality while achieving high model accuracy. The architecture supports real-time decision-making, minimizes network congestion, and enhances system resilience. Experimental analysis demonstrates that the proposed framework significantly reduces privacy risks while maintaining competitive predictive performance in smart manufacturing, healthcare, smart cities, and industrial IoT applications.

Disclaimer: Curated by HT Syndication.