一种基于好奇心驱动和深度强化学习的XSS自动化测试方法
By employing curiosity-driven and deep reinforcement learning methods, an intelligent agent is constructed to explore injection points on web pages and generate attack vectors. This solves the problem of incomplete information collection in existing automated XSS testing tools for dynamic web applications, and achieves efficient and automated XSS vulnerability detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SICHUAN UNIV
- Filing Date
- 2024-11-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing automated XSS testing tools struggle to handle dynamic navigation hidden pages in dynamic web applications, resulting in incomplete collection of injection point information, low vulnerability detection rates, and the need for manual intervention to train the agent, thus failing to achieve true automated detection.
By employing a curiosity-driven and deep reinforcement learning approach, an intelligent agent is constructed to explore injection points on web pages, and attack vectors are generated through deep reinforcement learning to achieve automated testing without human intervention.
It improves the coverage and accuracy of XSS injection points, generates high-quality attack vectors, enhances the effectiveness of vulnerability discovery and testing efficiency, and achieves rapid convergence without human intervention.
Smart Images
Figure CN119652572B_ABST