信息安全研究2025，Vol.11Issue(8)：761-767,7.DOI:10.12379/j.issn.2096-1057.2025.08.10
基于LSTM和CNN的对抗性跨站脚本攻击分析和检测方法研究
Research on Analysis and Detection Methods of Adversarial Cross-site Scripting Attacks Based on LSTM and CNN
摘要
Abstract
In recent years,machine learning and deep learning techniques have achieved significant success in detecting cross-site scripting(XSS)attacks.However,they still face challenges in defending adversarial attacks.To address this issue,this paper proposes an optimized method based on soft actor-critic(SAC)reinforcement learning combined with long short-term memory(LSTM)and convolutional neural network(CNN).Firstly,adversarial samples are generated by leveraging the SAC and LSTM-CNN detection model to simulate attacker strategies.These samples are then used for incremental training of the detection model,progressively narrowing the adversarial data generation space and improving the model's robustness and detection accuracy.Experimental results show that the generated adversarial data achieves an evasion success rate of over 90％across multiple detection tools.After incremental training,the detection model's defense capability against adversarial XSS attacks is significantly enhanced,with the evasion rate continuously decreasing.关键词
跨站脚本攻击/SAC/长短期记忆网络/卷积神经网络/对抗性攻击Key words
cross-site scripting/soft actor-critic/long short-term memory network/convolutional neural network/adversarial attacks分类
信息技术与安全科学引用本文复制引用
宋雨濛,龚元丽,任艳..基于LSTM和CNN的对抗性跨站脚本攻击分析和检测方法研究[J].信息安全研究,2025,11(8):761-767,7.基金项目
云南财经大学研究生创新基金项目(2024YUFEYC074) （2024YUFEYC074）
