Adversarial Attacks Against Deep Learning-Based Network Intrusion Detection Systems and Defense Mechanisms

Neural networks (NNs) are increasingly popular in developing NIDS, yet can prove vulnerable to adversarial examples. Through these, attackers that may be oblivious to the precise mechanics of the targeted NIDS add subtle perturbations to malicious traffic features, with the aim of evading detection and disrupting critical systems. Defending against such adversarial attacks is of high importance, but requires to address daunting challenges. Here, we introduce TIKI-TAKA, a general framework for (i) assessing the robustness of state-of-the-art deep learning-based NIDS against adversarial manipulations, and which (ii) incorporates defense mechanisms that we propose to increase resistance to attacks employing such evasion techniques. Specifically, we select five cutting-edge adversarial attack types to subvert three popular malicious traffic detectors that employ NNs. We experiment with publicly available datasets and consider both one-to-all and one-to-one classification scenarios, i.e., discriminating illicit vs benign traffic and respectively identifying specific types of anomalous traffic among many observed. The results obtained reveal that attackers can evade NIDS with up to 35.7% success rates, by only altering time-based features of the traffic generated. To counteract these weaknesses, we propose three defense mechanisms: model voting ensembling, ensembling adversarial training, and query detection. We demonstrate that these methods can restore intrusion detection rates to nearly 100% against most types of malicious traffic, and attacks with potentially catastrophic consequences (e.g., botnet) can be thwarted. This confirms the effectiveness of our solutions and makes the case for their adoption when designing robust and reliable deep anomaly detectors.