用强化学习生成绕过检测的跨站脚本攻击，逃逸率超96%。
Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study
- 用深度强化学习迭代优化恶意代码，实现自动化攻击向量生成。
- 修复原有方法缺陷后，攻击逃逸率提升至96%以上。
- 提出新评估框架，适合安全研究人员测试模型鲁棒性。
跨站脚本（XSS）对网页应用安全构成重大威胁。尽管深度学习在检测XSS攻击方面表现优异，但因其输入（攻击载荷）与输出（模型判断是否为恶意）之间的映射具有不连续性，仍易受对抗攻击影响。现有对抗攻击采用基于变异的策略，针对XSS攻击向量的不同组件进行迭代优化，使攻击者能持续规避检测。本文复现了当前最先进的XSS对抗攻击方法，揭示了原研究中的有效性威胁，并在此基础上提出更有效的评估策略。此外，我们引入了一个XSS Oracle以缓解这些问题。实验结果表明，在修正原有技术缺陷后，本方法的攻击逃逸率超过96%。
原文摘要 · Abstract (English)
Cross-site scripting (XSS) poses a significant threat to web application security. While Deep Learning (DL) has shown remarkable success in detecting XSS attacks, it remains vulnerable to adversarial attacks due to the discontinuous nature of the mapping between the input (i.e., the attack) and the output (i.e., the prediction of the model whether an input is classified as XSS or benign). These adversarial attacks employ mutation-based strategies for different components of XSS attack vectors, allowing adversarial agents to iteratively select mutations to evade detection. Our work replicates a state-of-the-art XSS adversarial attack, highlighting threats to validity in the reference work and extending it towards a more effective evaluation strategy. Moreover, we introduce an XSS Oracle to mitigate these threats. The experimental results show that our approach achieves an escape rate above 96% when the threats to validity of the replicated technique are addressed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。