Explainable AI for Deep Learning-Based Intrusion Detection Systems: A Comparative Analysis of SHAP and LIME with Robustness Evaluation
Deep learning provides better precision to intrusion detection systems, but the so-called black-box character of these models compromises trust. This paper offers a comparative framework of XAI methods assessment, and bridges standardized metrics and robustness testing loopholes. We include an evaluation methodology that uses fidelity, stability, latency, and robustness measures; an experimental study that compares SHAP and LIME on a BiLSTM model that is trained on CIC-IDS2017 on six attack types; and the first systematic measure of robustness of XAI explanations to adversarial perturbations. Findings indicate that both approaches obtain fidelity of over 0.92 with SHAP being 23 and 18 percent more stable and robust respectively in adversarial settings, though with 5.7 times higher latency. The quality of explanations depends on the attack. These results give practical recommendations on the selection of XAI and point out weaknesses in existing methods of explanation.