Enhancing Intrusion Detection in Mobile Ad-Hoc Networks: Comparative Study of Behavioral IDSs

Abstract

With an emphasis on behavioral intrusion detection systems [BIDSs], this study investigates the field of intrusion detection in mobile ad hoc networks [MANETs]. Because they are dynamic and decentralized, MANETs are vulnerable to a range of security risks, such as infiltration attempts. In this situation, conventional intrusion detection techniques show their shortcomings, opening the door for BIDS research. We provide a thorough comparison study of several intrusion detection system [IDS] methods, such as behavioral analysis, rule-based detection, machine learning-based detection, statistical anomaly detection, and environmental-based detection. These techniques are assessed in a dynamic network setting that considers the increasing volume of data and sporadic changes in sensor characteristics. The simulation becomes more realistic with the addition of behavior scores, which complicate the intrusion detection procedure Among the evaluation criteria are detection rates, which provide information about how well each IDS strategy performs in dynamic MANETs. The results contribute to the ongoing effort to improve security in MANETs by highlighting the advantages and disadvantages of the various intrusion detection approaches.