Unveiling the potential of Graph Neural Networks for robust Intrusion Detection
This addresses the need for robust intrusion detection in real networks, offering a novel approach to improve security against adversarial threats.
The paper tackles the problem of network intrusion detection systems (NIDS) being vulnerable to adversarial attacks by proposing a Graph Neural Network (GNN) model that captures structural patterns between flows. The results show the GNN achieves state-of-the-art accuracy on the CIC-IDS2017 dataset and maintains accuracy under adversarial attacks, while existing methods degrade by up to 50% in F1-score.
The last few years have seen an increasing wave of attacks with serious economic and privacy damages, which evinces the need for accurate Network Intrusion Detection Systems (NIDS). Recent works propose the use of Machine Learning (ML) techniques for building such systems (e.g., decision trees, neural networks). However, existing ML-based NIDS are barely robust to common adversarial attacks, which limits their applicability to real networks. A fundamental problem of these solutions is that they treat and classify flows independently. In contrast, in this paper we argue the importance of focusing on the structural patterns of attacks, by capturing not only the individual flow features, but also the relations between different flows (e.g., the source/destination hosts they share). To this end, we use a graph representation that keeps flow records and their relationships, and propose a novel Graph Neural Network (GNN) model tailored to process and learn from such graph-structured information. In our evaluation, we first show that the proposed GNN model achieves state-of-the-art results in the well-known CIC-IDS2017 dataset. Moreover, we assess the robustness of our solution under two common adversarial attacks, that intentionally modify the packet size and inter-arrival times to avoid detection. The results show that our model is able to maintain the same level of accuracy as in previous experiments, while state-of-the-art ML techniques degrade up to 50% their accuracy (F1-score) under these attacks. This unprecedented level of robustness is mainly induced by the capability of our GNN model to learn flow patterns of attacks structured as graphs.