Intrusion Detection using Network Traffic Profiling and Machine Learning for IoT

Abstract

The rapid increase in the use of IoT devices brings many benefits to the digital society, ranging from improved efficiency to higher productivity. However, the limited resources and the open nature of these devices make them vulnerable to various cyber threats. A single compromised device can have an impact on the whole network and lead to major security and physical damages. This paper explores the potential of using network profiling and machine learning to secure IoT against cyber-attacks. The proposed anomaly-based intrusion detection solution dynamically and actively profiles and monitors all networked devices for the detection of IoT device tampering attempts as well as suspicious network transactions. Any deviation from the defined profile is considered to be an attack and is subject to further analysis. Raw traffic is also passed on to the machine learning classifier for examination and identification of potential attacks. Performance assessment of the proposed methodology is conducted on the Cyber-Trust testbed using normal and malicious network traffic. The experimental results show that the proposed anomaly detection system delivers promising results with an overall accuracy of 98.35% and 0.98% of false-positive alarms.

Effectiveness Evaluation of Different IDSs Using Integrated Fuzzy MCDM Model

“…Figure 2 shows how to make a tree shape. This tree shape was created with the help of experts' opinions [34]. The triangular fuzzy number (TFN) is then constructed from the hierarchical structure.…”

“…It should be necessary to evaluate the effectiveness of different intrusion-detection systems [33,34]. A condition that is hard to ascertain is unsuitable for the job.…”

IMIDS: An Intelligent Intrusion Detection System against Cyber Threats in IoT

“…The experiments conducted on KDDCup99, NSL-KDD, and UNSW-NB15 yielded results of 98.85%, 97.55%, and 84.33%, respectively. The authors in [58] exploited incremental machine learning to build an effective network intrusion prevention system for IoT. The proposed system includes an online-cluster algorithm powered by the self-organizing incremental neural network and multiple support vector machines to classify the attacks.…”

An Intelligent Platform for Threat Assessment and Cyber-Attack Mitigation in IoMT Ecosystems

“…The superiority of anomaly-based techniques in detecting unknown attacks and their ability to adopt to the operational environment makes them ideal for the IoMT ecosystem. Several intelligent intrusion detection systems have been proposed relying on different ML or deep learning (DL) algorithms [1,3,19,25]. Recent studies have also considered using FL approaches to improve IDS performance for the IoMT -see e.g.…”