Data Flooding Intrusion Detection System for MANETs Using Deep Learning Approach

Abstract

Today mobile ad hoc networks (MANETs) and its derivatives such as vehicular ad-hoc networks (VANETs), wireless sensor network (WSN), are more interesting subject for researchers, seen particularly from the appearance of the paradigm of smart cities, smart homes, and Internet of Things (IoT). In addition to this widespread use, several vulnerabilities and attacks appear like for instance black hole attack and data flooding attack. Nevertheless, the limitations of hardware generally used in MANETs make many views the tasks of detection and countermeasure of attacks. In this paper, using the technology of deep neural network (DNN) deep learning, we try to propose an intrusion detection system (IDS) for the subclass of the big class DDoS: Data flooding attack, with using the dataset CICDDoS2019. Our obtained results show that the proposed architecture model can achieve very interesting performance (Accuracy, Precision, Recall and F1-score).