Talk, Matinée IA && Cybersécurité, Programme de Transfer du Campus Cyber, La Défense, France
Presentation of the paper “Breaking GNN-based NIDS via Hard-Label Black-Box Flow Injection Attacks” at the PTTC (Programme de Transfer du Campus Cyber) on September 24, 2026. The talk was presented for an mixed audience of researchers and industry professionals.
Talk, ESORICS, European Symposium on Research in Computer Security, Rome, Italy
While Graph Neural Network (GNN)-based Network Intrusion Detection Systems (NIDS) excel by encoding relational traffic struc- tures, this structural dependency introduces novel adversarial vulner- abilities. Existing graph attacks remain impractical, often demanding white-box access, prohibitive query budgets, or exploit-breaking payload manipulations. To overcome these limitations, we propose a practical, hard-label black-box attack that evades detection strictly by injecting valid supplementary traffic flows, perfectly preserving the exploit’s func- tional integrity. By formulating this combinatorial challenge as a weakly submodular maximization problem, we leverage a local surrogate GNN and an influence-guided greedy search to efficiently identify highly impactful injections. We theoretically prove this approach yields a strict polynomial-time approximation guarantee. Empirically, we demonstrate the proposed flow injection attack can bypass state-of-the-art GNN-based NIDS with minimal query budgets
Talk, SECRYPT, International Conference on Security and Cryptography, Porto, Portugal
This paper investigates the robustness of Graph Neural Network-based Network Intrusion Detection Systems (GNN-NIDS) against adversarial flow injection attacks. We propose a novel attack strategy that leverages the structural properties of network traffic graphs to evade detection. Our evaluation demonstrates the effectiveness of the proposed attack and highlights the need for improved defense mechanisms in GNN-NIDS.