Launching Adversarial Attacks against Network Intrusion Detection Systems for IoT

TL;DR

This paper evaluates the robustness of machine learning-based IoT network intrusion detection systems against adversarial attacks, demonstrating that attackers can effectively evade detection using poisoning and gradient sign methods.

Contribution

It introduces a comprehensive evaluation of both traditional and deep learning intrusion detection models' vulnerability to adversarial attacks in IoT environments.

Findings

Adversarial attacks can significantly reduce detection accuracy.

Poisoning and gradient sign methods are effective in evading detection.

Traditional models are also vulnerable to adversarial manipulation.

Abstract

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought. Traditional defending approaches are no longer sufficient to detect both known and unknown attacks to high accuracy. Machine learning intrusion detection systems have proven their success in identifying unknown attacks with high precision. Nevertheless, machine learning models are also vulnerable to attacks. Adversarial examples can be used to evaluate the robustness of a designed model before it is deployed. Further, using adversarial examples is critical to creating a robust model designed for an adversarial environment. Our work evaluates both traditional machine learning and deep learning models' robustness using the Bot-IoT dataset. Our methodology included two main approaches. First, label poisoning, used to cause incorrect classification by the model. Second, the fast gradient sign method, used to evade detection measures. The experiments demonstrated that an attacker could manipulate or circumvent detection with significant probability.