Understanding the Adversary: A Survey of Adversarial Machine Learning in Network Intrusion Detection

Adversarial machine learning (AML) is a growing threat to network intrusion detection systems (NIDS). However, the literature remains fragmented across models, datasets, and evaluation practices. This survey provides the first comprehensive post-2021 synthesis of AML for machine learningbased NIDS, consolidating 94 peer-reviewed studies (2022-2025) within a unified hierarchical taxonomy integrating threat-model assumptions, methodological strategies, and evaluation outcomes. Our analysis reveals persistent biases toward feature-space manipulation, dataset-specific dependencies, overly optimistic assumptions about adversary knowledge, and evasion-centric evaluation methodologies. It also identifies emerging trends, including ensemble-based defenses, IoT/ICS data realism, and enhanced reproducibility. Combining conceptual and quantitative perspectives, we establish a reproducible research mapping framework that identifies six open challenges defining the next stage of adversarially robust intrusion detection. Thus, we provided a roadmap toward trustworthy, empirically grounded, and operationally viable AML-NIDS in adversarial settings.