Implementing Practical Problem-Space Adversarial Attacks on Modern Network Intrusion Detection Systems

This paper proposes a novel approach to adversarial attacks against machine learning-based network intrusion detection systems (NIDS). Unlike conventional methods that apply feature-space perturbations, we implement realistic problem-space attacks by manipulating network traffic through advanced packet modification techniques using the Scapy framework. Our methodology targets multiple attack vectors, including recon-naissance, data exfiltration, and command and control communications. Experiments evaluate four popular machine learning models (GBDT, DNN, Random Forest, and SVM) against both legitimate and adversarially manipulated traffic. Results demonstrate significant detection performance degradation across all models, with evasion rates reaching 72% for reconnaissance traffic. We observe strong transferability of adversarial examples between different model architectures and analyze the underlying mechanisms through feature space visualization. Our findings highlight fundamental vulnerabilities in ML-based intrusion detection and emphasize the need for defensive techniques specifically addressing realistic traffic manipulations rather than abstract feature perturbations.