Jul 2026· IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies· pp. 119-124· 0 citations· 21 references
Abstract
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.
The proposed adversarially trained ensemble achieves the strongest overall trade-off between classification performance on the robustness evaluation set and evasion resistance, reducing the average ASR from 0.41 to 0.03 and achieving an RI of 0.98.
This study investigates the transferability of adversarial attacks across XGBoost and LightGBM models in IDS and uses Explainable AI (XAI) techniques to identify features that influence model decisions and shows that feature-importance patterns can be used to examine model vulnerability under adversarial perturbations.
Abdlelah Abdlatef, Marwa D. Abdulkareem, Duygu Çakır· International Journal of Inf...· 1 citation
A comparative experimental study of anomaly and threat detection techniques used in network analysis through a multistep pipeline, demonstrating that hybrid architectures achieve superior generalisation, yet face challenges regarding computational overhead and cross-dataset adaptability.
Antonio Lara-Gutierrez, Carmen Fernandez-Gago, J. A. Onieva· Artificial Intelligence Revi...· 0 citations
A sensitivity-driven adversarial generation framework (AGF) that identifies and perturbs the most influential traffic features that affect the classifier’s decision boundary to generate statistically consistent adversarial samples with constrained perturbation magnitude is proposed.
Omar Abboosh Hussein Gwassi, O. N. Uçan· IEEE Access· 0 citations
This study evaluates the robustness of multimodal learning-based IDS against transferable adversarial examples (AEs) generated by Generative Adversarial Networks (GANs) and integrates adversarial training techniques to enhance the IDS’s capability to identify attack patterns with small perturbations.
Duy The Phan, Cao The Thuan, Q. Doan et al.· Journal on spesial topics in...· 0 citations
The study demonstrates that integrating deep learning with stable explainable AI offers a practical and trustworthy solution for zero-day intrusion detection, contributing validated evidence to an area where explanation reliability is rarely examined.
Sumayyamol Mukkil Muhammed Ismail, M. Ahmed, S. Begum· Applied Informatics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
