对抗鲁棒性与可解释性漂移的实证分析：在网络安全分类器中的应用
Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers
AI总结：
本文通过实证研究分析了网络安全分类器中对抗鲁棒性与可解释性漂移的问题，提出鲁棒性指数指标，并展示了对抗训练对提升鲁棒性的效果。
摘要：
机器学习（ML）模型越来越多地应用于网络安全领域，如钓鱼网站分类和网络入侵检测。然而，这些模型仍然容易受到对抗性扰动的影响，即微小的、故意的输入修改会降低检测准确性和影响可解释性。本文对两个网络安全领域进行了实证研究：钓鱼URL分类和网络入侵检测，探讨了L（无穷）有界快速梯度符号法（FGSM）和投影梯度下降（PGD）扰动对模型准确率的影响，并引入了一个定量指标，即鲁棒性指数（RI），定义为准确率扰动曲线下的面积。基于梯度的特征敏感性和SHAP基于的归因漂移分析揭示了哪些输入特征最易受到对抗性操控。在Phishing Websites和UNSW NB15数据集上的实验显示了一致的鲁棒性趋势，对抗训练使RI提高了最高9%，同时保持干净数据的准确率。这些发现突显了鲁棒性和可解释性退化之间的耦合，并强调了在设计可信的、基于AI的网络安全系统时定量评估的重要性。
英文摘要：
Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulnerable to adversarial perturbations small, deliberate input modifications that can degrade detection accuracy and compromise interpretability. This paper presents an empirical study of adversarial robustness and explainability drift across two cybersecurity domains phishing URL classification and network intrusion detection. We evaluate the impact of L (infinity) bounded Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) perturbations on model accuracy and introduce a quantitative metric, the Robustness Index (RI), defined as the area under the accuracy perturbation curve. Gradient based feature sensitivity and SHAP based attribution drift analyses reveal which input features are most susceptible to adversarial manipulation. Experiments on the Phishing Websites and UNSW NB15 datasets show consistent robustness trends, with adversarial training improving RI by up to 9 percent while maintaining clean-data accuracy. These findings highlight the coupling between robustness and interpretability degradation and underscore the importance of quantitative evaluation in the design of trustworthy, AI-driven cybersecurity systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
