Network Intrusion Detection for IoT Security Based on Learning Techniques

作者：Nadia Chaabouni, Mohamed E. Mosbah, Akka Zemmari, Cyrille Sauvignac, Parvez Faruki · 发表于：IEEE Communications Surveys & Tutorials · 年份：2019 · DOI：10.1109/comst.2019.2896380 · 被引用次数：946 · 研究领域：Network Security and Intrusion Detection、Advanced Malware Detection Techniques、Internet Traffic Analysis and Secure E-voting

Pervasive growth of Internet of Things (IoT) is visible across the globe. The 2016 Dyn cyberattack exposed the critical fault-lines among smart networks. Security of IoT has become a critical concern. The danger exposed by infested Internet-connected Things not only affects the security of IoT but also threatens the complete Internet eco-system which can possibly exploit the vulnerable Things (smart devices) deployed as botnets. Mirai malware compromised the video surveillance devices and paralyzed Internet via distributed denial of service attacks. In the recent past, security attack vectors have evolved bothways, in terms of complexity and diversity. Hence, to identify and prevent or detect novel attacks, it is important to analyze techniques in IoT context. This survey classifies the IoT security threats and challenges for IoT networks by evaluating existing defense techniques. Our main focus is on network intrusion detection systems (NIDSs); hence, this paper reviews existing NIDS implementation tools and datasets as well as free and open-source network sniffing software. Then, it surveys, analyzes, and compares state-of-the-art NIDS proposals in the IoT context in terms of architecture, detection methodologies, validation strategies, treated threats, and algorithm deployments. The review deals with both traditional and machine learning (ML) NIDS techniques and discusses future directions. In this survey, our focus is on IoT NIDS deployed via ML since learning algorithms ...