Intrusion Detection and Prevention in WSN and MANET using Machine Learning Techniques and Existing Challenges

Abstract

Intrusion detection and prevention are two wide terms describing application security practices deployed to alleviate attacks and prevent additional threats. The first is a reactive measure that detects ongoing attacks using an Intrusion Detection System (IDS). On the other hand, the second is a proactive security measure, which uses an Intrusion Prevention System (IPS) to preemptively block application attacks. Several projects have proposed various IDS and IPS methods for Wireless Sensor Network (WSN) and Mobile AdhocNETwork (MANET) as well. This paper tempts to analyze diverse techniques associated with IDS and IPS approaches deployed in WSN and MANET. It makes a review of 66 research papers and states the significant analysis. Initially, the analysis focuses on different papers relating to contributions and limitations of the adopted algorithms, and their simulation network environment. Later the performance measures computed in entire papers like energy efficiency, throughput, packet delivery ratio etc. are observed to validate its effectiveness. Moreover, the different types of existing attacks detected and prevented in both WSN and MANET are also analyzed. Later, the contribution of different optimization algorithms on IDS and IPS in various state-of-theart works is also reviewed. Finally, a detailed research gap is also depicted based on the development of intelligent methods concerning the unresolved challenges in IDS and IPS.