A Multifractal Analysis and Machine Learning Based Intrusion Detection System with an Application in a UAS/RADAR System

The rapid development of Internet Things (IoT) technology, together with mobile network has created a never-before-seen world interconnection, evoking research on how to make it vaster, faster, and safer. To support the ongoing fight against malicious misuse networks, in this paper we propose novel algorithm called AMDES (unmanned aerial system multifractal analysis intrusion detection system) for spoofing attack detection. This is based both wavelet leader (WLM) machine learning (ML) principles. In earlier unmanned systems (UAS), (IDS) (MF) spectral have been used provide accurate MF spectrum estimations traffic. Such an estimation then detect characterize flooding anomalies that can be observed vehicle (UAV) network. However, previous contributions lacked consideration other types intrusions commonly UAS such as man middle (MITM). work, promising methodology accommodated within UAS. highlights robust approach terms false positive performance detecting location reporting system.