2026· International Conference on Security and Cryptography· pp. 860-867· 0 citations· 24 references
Computer Science
TL;DR
A query-based black-box flow injection attack against GNN-based NIDS, where adversaries inject crafted traffic flows into existing communications to evade detection, is proposed.
Abstract
: Graph Neural Networks (GNNs) enhance Network Intrusion Detection Systems (NIDS) by leveraging structural relationships in network traffic, but this reliance introduces new vulnerabilities. In this paper, we propose a query-based black-box flow injection attack against GNN-based NIDS, where adversaries inject crafted traffic flows into existing communications to evade detection. Our experiments demonstrate that these constrained attacks are highly effective, frequently succeeding with a minimal budget of injected flows. Analysis reveals that local graph structural properties primarily determine attack success. Additionally, the attack demonstrates strong transferability across various GNN architectures, confirming the viability of a black-box threat. These findings highlight critical vulnerabilities in GNN-based NIDS, even when adversaries are restricted to purely additive flow injections.
Adversarial attacks pose a significant threat to machine learning-based network intrusion detection systems (NIDS) by injecting crafted perturbations into malicious traffic to evade detection. However, many existing attacks rely on per-flow optimization after observing complete flows, which incurs high computational co...
Zhu Gong, Wei Ji, Lu-Yao Liu et al.· IEEE Transactions on Informa...· 0 citations
The Hierarchical Adversarially-Driven Escalation System (hades) is introduced, a framework that addresses this vulnerability to adversarial examples through three coordinated mechanisms and maintains near-perfect detection accuracy under both normal and adversarial conditions.
A. Derhab, Adlen Kerboua, N. Seddari et al.· Computer Modeling in Enginee...· 0 citations
A new graph-guided contrastive transformer-based intrusion detection system (GCT-IDS) which aims at improving detection accuracy and robustness and preserving real-time feasibility is presented.
The proposed Collateral Damage Constrained Graph Backdoor Attack (CDCA) combines neighborhood-aware target node selection with a self-constrained trigger generation strategy to suppress trigger-induced propagation by enforcing prediction consistency on clean K -hop neighboring nodes.
Di Jin, Ze-Chuan Zhang, Bing-Dao Feng et al.· Proceedings of the Thirty-Fi...· 0 citations
Dynamic Multiscale Graph Contrastive Representation Learning (DMGCRL), a self-supervised framework that hierarchically models network intrusions at different levels, is proposed, which consistently outperforms SOTA methods in network intrusion detection.
Raeed Al-Sabri, Abdullatif Albaseer, Mohamed M. Abdallah et al.· IEEE Transactions on Network...· 0 citations
Encrypted communication protocols are increasingly being leveraged to evade traditional Intrusion Detection Systems (IDS), particularly through techniques such as DNS tunneling and DNS over HTTPS (DoH).However, the existing frameworks primarily focused on non-encrypted attack traffic and are operated as a black-box mod...
Rhithika M. Pradeep, Ron Binoy Mechery, Sreerag K et al.· International Conference Inn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
