A Novel Ensemble of Hybrid Intrusion Detection System for Detecting Internet of Things Attacks

• DOI: 10.3390/electronics8111210
• Publication Date: 2019-10-25T07:20:36Z
• Authors: Ansam Khraisat; Iqbal Gondal; Peter Vamplew; Joarder Kamruzzaman; Ammar Alazab
• Keywords: False positive rate

The Internet of Things (IoT) has been rapidly evolving towards making a greater impact on everyday life to large industrial systems. Unfortunately, this attracted the attention cybercriminals who made IoT target malicious activities, opening door possible attack end nodes. Due number and diverse types devices, it is challenging task protect infrastructure using traditional intrusion detection system. To novel ensemble Hybrid Intrusion Detection System (HIDS) proposed by combining C5 classifier One Class Support Vector Machine classifier. HIDS combines advantages Signature (SIDS) Anomaly-based (AIDS). aim framework detect both well-known intrusions zero-day attacks with high accuracy low false-alarm rates. evaluated Bot-IoT dataset, which includes legitimate network traffic several attacks. Experiments show that hybrid IDS provide higher rate lower false positive compared SIDS AIDS techniques.