A New Intrusion Detection Method Based on Machine Learning in Mobile Ad Hoc NETwork

In a Mobile Ad hoc NETwork (MANET), intrusion detection is of significant importance in many applications in detecting malicious or unexpected intruder (s). The intruder can be an enemy in a battlefield, or a malicious moving object in the area of interest. Unfortunately, many anomaly intrusion detection systems (IDS) take on higher false alarm rate (FAR) and false negative rate (FNR). In this paper, we propose and implement a new intrusion-detection system using Adaboost, a prevailing machine learning algorithm, and its detecting model adopts a dynamic load-balancing algorithm, which can avoid packet loss and false negatives in high-performance severs with handling heavy traffic loads in real-time and can enhance the efficiency of detecting work. Compared to contemporary approaches, our system demonstrates an especially low false positive rate and false negative rate in certain circumstances while does not greatly affect the network performance.