9 papers
Refploit: Facilitating Exploit Construction via Code-Agent Trajectory Repair
Zirui Chen, Zhipeng Xue, Jiayuan Zhou +3
Vulnerability exploits play a crucial role in assessing the downstream impact of Java library vulnerabilities. While some vulnerabilities are accompanied by disclosed exploit refer…
CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
Hanrong Zhang, Shicheng Fan, Henry Peng Zou +12
Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained func…
Mitigating Implicit Inconsistencies in Patch Porting
Shengyi Pan, Zhongxin Liu, Jiayuan Zhou +3
Promptly porting patches from a source codebase to its variants (e.g., forks and branches) is essential for mitigating propagated defects and vulnerabilities. Recent studies have e…
Assessing the Cross-Version Applicability of Java Library Vulnerability Exploits
Zirui Chen, Qi Zhan, Jiayuan Zhou +3
Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulne…
Multi-Agent End-to-End Vulnerability Management for Mitigating Recurring Vulnerabilities
Zelong Zheng, Jiayuan Zhou, Xing Hu +2
Software vulnerability management has become increasingly critical as modern systems scale in size and complexity. However, existing automated approaches remain insufficient. Tradi…
Diffploit: Facilitating Cross-Version Exploit Migration for Open Source Library Vulnerabilities
Zirui Chen, Zhipeng Xue, Jiayuan Zhou +3
Exploits are commonly used to demonstrate the presence of library vulnerabilities and validate their impact across different versions. However, their direct application to alternat…