4 papers
Contextualizing Sink Knowledge for Java Vulnerability Discovery
Fabian Fleischer, Cen Zhang, Joonun Jang +3
Java applications are prone to vulnerabilities stemming from the insecure use of security-sensitive APIs, such as file operations enabling path traversal or deserialization routine…
Patch Validation in Automated Vulnerability Repair
Zheng Yu, Wenxuan Shi, Xinqian Sun +3
Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in patching vulnerabilities -- that is,…
PortGPT: Towards Automated Backporting Using Large Language Models
Zhaoyang Li, Zheng Yu, Jingyi Song +3
Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). Howe…
Agentic Specification Generator for Move Programs
Yu-Fu Fu, Meng Xu, Taesoo Kim
While LLM-based specification generation is gaining traction, existing tools primarily focus on mainstream programming languages like C, Java, and even Solidity, leaving emerging a…