Decentralized Machine Learning for Hybrid Intrusion Detection System to Spot Cyber Attacks

ABSTRACT

Network security and privacy are greatly enhanced by a Hybrid Intrusion Detection system(HID). HID system architecture consists of a central server and multiple agents deployed across the network to collect data from various sources. The collected data is analyzed using rule-based and machine learning techniques to identify potential threats. Alerts are then sent to the central server, which distributes them to the relevant agents for further analysis and response. A hybrid approach that combines rule-based and machine learning algorithms to achieve better detection rates and reduce false positives. Hybrid intrusion detection system that combines rule-based detection and machine learning algorithms for better detection and prevention of cyber-attacks in real time. A distributed architecture is needed to share real-time threat intelligence among numerous nodes with decentralized storage and distribution of alerts, to improve scalability and availability. By using machine learning algorithms, train a large dataset of normal and attack traffic, to learns the system continuously and adapts to techniques. The use of decentralized storage ensures that alerts are always available, even in the event of network disruptions or server failures. The proposed system is by various performance metrics, including detection rate, false positive rate, and response time .Results show that the system achieves high detection rates while minimizing false positives and response times.

FULL TEXT