An Enhanced Data Privacy and Security Mitigation Technique: A Novel Federated Deep Learning (FDL) Model for Intrusion detection and Classification System For Cyber -Physical Systems in Internet of things (IoTs)

Abstract

The Internet of Things (IoT) has faced difficulties in its adoption because of security and data privacy issues that exist in the modern technological environment. Modern cybersecurity systems face multiple problems due to the fast-paced development of cyber threats. The research examines the issue where modern breach methods surpass traditional defense systems. Through federated learning, multiple clients train global models together by sharing machine learning without having to exchange actual data. The document emphasized that security functions as a vital component throughout End-to-End data security configurations. FL operates as an autonomous framework that provides improved data security through decentralized IDS training mechanisms implemented across separate connected devices. This paper analyzes Federated Learning methods and Virtual security protocols which demonstrate their vital role in modern networking infrastructure for establishing secure data transfer on unsecured internet networks. The paper explores the new difficulties that confront Machine Learning model implementations. These techniques help analyze large datasets from IoT devices that connect to the internet due to their effectiveness in processing internet-based application data. A Federated CNN model will serve as an effective system in the future to detect cyber threat identification.