Matthieu Mouzaoui

Matthieu Mouzaoui

PhD Student in Inria PIRAT team

Publications

Conference Papers

Breaking GNN-based NIDS via Hard-Label Black-Box Flow Injection Attacks

Published in ESORICS, European Symposium on Research in Computer Security, 2026

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

Recommended citation: Mouzaoui, M., Han, Y., Blanc, G., Rilling, G., Hurfin, M. (2027). Breaking GNN-Based NIDS via Hard-Label Black-Box Flow Injection Attacks. In: Spognardi, A., Sun, K., De Gaspari, F., Mancini, L.V. (eds) Computer Security – ESORICS 2026. ESORICS 2026. Lecture Notes in Computer Science, vol 16970. Springer, Cham. https://doi.org/10.1007/978-3-032-38702-8_13
Download Paper | Download Slides

Robustness Evaluation of Graph Neural Network-based Network Intrusion Detection Systems against Adversarial Flow Injection

Published in SECRYPT, International Conference on Security and Cryptography, 2026

Position paper for SECRYPT 2026. 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.

Recommended citation: Mouzaoui, M.; Han, Y.; Blanc, G.; Rilling, G. and Hurfin, M. (2026). Robustness Evaluation of Graph Neural Network-Based Network Intrusion Detection Systems against Adversarial Flow Injection. In Proceedings of the 23rd International Conference on Security and Cryptography - Volume 1, ISBN 978-989-758-858-7, ISSN 2184-7711, pages 860-867.
Download Paper | Download Slides