Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks
This addresses security risks for network intrusion detection systems using GNNs, representing an incremental advancement by focusing on a new attack type.
The paper tackles the vulnerability of Graph Neural Network (GNN)-based Network Intrusion Detection Systems (NIDS) by formalizing and modeling structural adversarial attacks, demonstrating that these models are robust against feature-based attacks but susceptible to structure-based ones.
Machine Learning (ML) algorithms have become increasingly popular for supporting Network Intrusion Detection Systems (NIDS). Nevertheless, extensive research has shown their vulnerability to adversarial attacks, which involve subtle perturbations to the inputs of the models aimed at compromising their performance. Recent proposals have effectively leveraged Graph Neural Networks (GNN) to produce predictions based also on the structural patterns exhibited by intrusions to enhance the detection robustness. However, the adoption of GNN-based NIDS introduces new types of risks. In this paper, we propose the first formalization of adversarial attacks specifically tailored for GNN in network intrusion detection. Moreover, we outline and model the problem space constraints that attackers need to consider to carry out feasible structural attacks in real-world scenarios. As a final contribution, we conduct an extensive experimental campaign in which we launch the proposed attacks against state-of-the-art GNN-based NIDS. Our findings demonstrate the increased robustness of the models against classical feature-based adversarial attacks, while highlighting their susceptibility to structure-based attacks.