Machine learning (ML) has greatly improved intrusion detection in enterprise networks. However, ML models remain vulnerable to adversarial attacks, where small input changes cause misclassification. This study evaluates the robustness of a Random Forest (RF), a standard neural network (NN), and a Transformer-based Network Intrusion Detection System (NIDS). It also introduces ADVNN, an adversarially trained neural network designed to improve resilience. Model performance is tested using the UNSW-NB15 dataset under both clean and adversarial conditions. The attack types include Projected Gradient Descent (PGD), Fast Gradient Sign Method (FGSM), and Black-Box transfer attacks. The proposed ADVNN achieves 86. 04% accuracy on clean data. It maintains over 80% accuracy under PGD and FGSM attacks, and exceeds 85% under Black-Box attacks at ϵ=0. 15. In contrast, the RF, NN, and Transformer-based models suffer significant degradation under adversarial perturbations. These results highlight the need to incorporate adversarial defenses into ML-based NIDS for secure deployment in real-world environments.
Heydari et al. (Fri,) studied this question.