A Hybrid Data-driven Model for Intrusion Detection in VANET

• DOI: 10.1016/j.procs.2021.03.065
• Publication Date: 2021-05-18T04:27:03Z
• Authors: Hind Bangui; Mouzhi Ge; Barbora Buhnova
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Nowadays, VANET (Vehicular Ad-hoc NETwork) has gained increasing attention from many researchers with its various applications, such as enhancing traffic safety by collecting and disseminating event information. This increased interest in necessitated greater scrutiny of machine learning (ML) methods used for improving the security capabilities intrusion detection systems (IDSs), need to solve computationally intensive ML problems due vehicular data. Therefore, this paper, we propose a hybrid model enhance performance IDSs dealing explosive growth computing power detecting malicious incidents timely. The proposed approach mainly uses advantages Random Forest detect known network intrusions. Besides, there is post-detection phase possible novel intruders using coresets clustering algorithms. Our evaluated over very recent IDS dataset named CICIDS2017. preliminary results show that can increase utility IDSs.