Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS

--Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly in structured data like network traffic, where interdependent features complicate effective adversarial manipulations. Moreover, ambiguity in current approaches restricts reproducibility and limits progress in this field. Hence, existing defenses often fail to handle evolving adversarial attacks. This paper proposes a novel approach for black-box adversarial attacks, that addresses these limitations. Unlike prior work, which often assumes system access or relies on repeated probing, our method strictly respect black-box constraints, reducing interaction to avoid detection and better reflect real-world scenarios. We present an adaptive feature selection strategy using change-point detection and causality analysis to identify and target sensitive features to perturbations. This lightweight design ensures low computational cost and high deployability. Our comprehensive experiments show the attack's effectiveness in evading detection with minimal interaction, enhancing its adaptability and applicability in real-world scenarios. By advancing the understanding of adversarial attacks in network traffic, this work lays a foundation for developing robust defenses. N today's interconnected world, almost every aspect of our personal and professional lives is dependent on the digital infrastructure. Moreover, the growing volumes of sensitive data transmitted over networks present significant threats to privacy, security, and even national stability. Intrusion detection systems (IDS) play a vital role in safeguarding networks by continuously monitoring the network traffic for suspicious activities [1]. To fill this void, integrating machine learning (ML) with IDS has revolutionized network security, offering proactive detection by analyzing large traffic datasets, learning patterns, and identifying potential breaches [2]. Critically, the increasing adoption of ML-based IDS has exposed them to adversarial attacks, where slight perturbations could easily trick ML models into making wrong predictions [3]. This threat has been initially developed in the image classification context (i.e., unstructured data) without considering specific feature importance [4], [5].