EUVIMEDEUVIMED entdecken
Crossref

Generative Red Teaming for Robust Network Intrusion Detection: A Constrained Adversarial Approach

Mohammad Noroozi, Jalal Ghadermazi, Soumyadeep Hore, Ankit Shah, Nathaniel Bastian

ACM Transactions on Internet Technology · 21.11.2026

DOI: 10.1145/3871042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Internet Technology, online erschienen am 21.11.2026. Verfasst von Mohammad Noroozi und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing reliance on digital infrastructure has made the protection of critical networks essential for ensuring operational resilience and security. Cybersecurity operations centers (CSOCs), supported by advanced technologies and skilled professionals, are central to this effort, with network intrusion detection systems (NIDS) serving as a primary defense mechanism. The adoption of machine learning (ML) and deep learning (DL) within NIDS has greatly improved their ability to detect cyber threats. However, these models are inherently vulnerable to adversarial attacks, where carefully crafted inputs manipulate model weaknesses to evade detection. The rapid evolution of generative artificial intelligence (AI) technologies has amplified this risk by enabling adversaries to automate the creation of sophisticated evasion attacks. Hence, it is critical to evaluate the robustness of ML/DL-based NIDS against evolving adversaries. Current adversarial evaluation techniques for NIDS fail to capture real-world constraints, leading to unrealistic assumptions such as unrestricted packet modifications and control over encrypted communications, resulting in a false sense of security. To bridge this gap, we introduce a generative red teaming framework designed to conduct realistic and scalable vulnerability assessment of ML/DL-based NIDS. Our adversarial framework, PerturbLite , leverages a novel autoencoder-based generative model that produces minimally perturbed, functionality-preserving adversarial network packets capable of bypassing detection. Extensive experiments on real-world benchmarking network intrusion data sets reveal that our approach achieves superior evasion performance while maintaining packet validity, often altering less than 1% of the original content. In addition to outperforming existing adversarial methods, our framework uncovers systemic vulnerabilities within NIDS, offering insights that can guide the design of more resilient detection models at a CSOC to better protect organizations. Our work advances adversarial testing methodologies in cybersecurity and aligns with best practices recommended by Cybersecurity and AI governance frameworks.

Zitieren

APA

Noroozi, M., Ghadermazi, J., Hore, S., Shah, A., & Bastian, N. (2026). Generative Red Teaming for Robust Network Intrusion Detection: A Constrained Adversarial Approach. ACM Transactions on Internet Technology. https://doi.org/10.1145/3871042

Vancouver

Noroozi M, Ghadermazi J, Hore S, Shah A, Bastian N. Generative Red Teaming for Robust Network Intrusion Detection: A Constrained Adversarial Approach. ACM Transactions on Internet Technology. 2026. doi:10.1145/3871042

BibTeX
@article{Noroozi2026,
  author = {Noroozi, Mohammad and Ghadermazi, Jalal and Hore, Soumyadeep and Shah, Ankit and Bastian, Nathaniel},
  title = {Generative Red Teaming for Robust Network Intrusion Detection: A Constrained Adversarial Approach},
  journal = {ACM Transactions on Internet Technology},
  year = {2026},
  doi = {10.1145/3871042}
}
Kostenlos starten →