Anomaly Detection System for Ad Hoc Network Using Bayesian Networks

Abstract

Ad Hoc Networks are extremely vulnerable to attacks due to their dynamically changing topology, absence of conventional security infrastructures, and vulnerability of nodes, vulnerability of channels and open medium of communication. The Internet and computer networks are exposed to an increasing number of security threats continuously. With new types of attacks appearing almost every day, developing more powerful and self learning Intrusion Detection System (IDS) is a great challenge and a need. Thus, anomaly-based intrusion detection techniques are a valuable technology to protect target systems and networks against malicious and unauthorized activities because anomaly detection system can detect the novel attacks which are not detected by the signature based IDS. The ever growing new intrusion types pose a serious problem for their detection. The human involvement is usually tedious, time consuming and expensive. Hence the need of Machine Learning comes into focus. Signature based IDS has the inability to detect new variants of the attack. Machine Learning techniques are in use due to the ability of these algorithms to generalize (a multiplicity of soft constraints rather than a few hard constraints) and to adapt (updates based on new training instances).