NAttack! Adversarial Attacks to bypass a GAN based classifier trained to detect Network intrusion

Abstract

With the recent developments in artificial intelligence and machine learning, anomalies in network traffic can be detected using machine learning approaches. Before the rise of machine learning, network anomalies which could imply an attack, were detected using well-crafted rules. An attacker who has knowledge in the field of cyber-defence could make educated guesses to sometimes accurately predict which particular features of network traffic data the cyber-defence mechanism is looking at. With this information, the attacker can circumvent a rule-based cyber-defense system. However, after the advancements of machine learning for network anomaly, it is not easy for a human to understand how to bypass a cyber-defence system. Recently, adversarial attacks have become increasingly common to defeat machine learning algorithms. In this paper, we show that even if we build a classifier and train it with adversarial examples for network data, we can use adversarial attacks and successfully break the system. We propose a Generative Adversarial Network(GAN)based algorithm to generate data to train an efficient neural network based classifier, and we subsequently break the system using adversarial attacks.