Intrusion Detection in Sensor Networks Using Clustering and Immune Systems

Abstract

Security of sensor networks is a complicated task, mostly due to the limited resources of sensor units. Encryption and authentication are useless if an attacker has entered the system. Thus, a second line of defense known as Intrusion Detection must be added in order to detect and eliminate attacks. In the recent past, various solutions for detecting intrusions have been proposed. Most of them are able to detect only a limited number of attacks. The solutions that deploy machine learning techniques exhibit higher level of flexibility and adaptability. Yet, these techniques consume significant power and computational resources. In this work we propose to implement unsupervised algorithms (genetic algorithm and self-organized maps) for detecting intrusions using the energy-efficient SORU architecture. Separate detectors are further organized in a distributed system using the idea of immune system organization. Our solution offers many benefits: ability to detect unknown attacks, high adaptability and energy efficiency. First testing results obtained in real environment demonstrate its high potential.