4 papers
A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection
Siyi Chen, Tianhan Luo, Shijian Wu +4
Open-source libraries are widely used in modern software development, introducing significant security vulnerabilities. While static analysis tools can identify potential vulnerabi…
SecCodeBench-V2 Technical Report
Longfei Chen, Ji Zhao, Lanxiao Cui +24
We introduce SecCodeBench-V2, a publicly released benchmark for evaluating Large Language Model (LLM) copilots' capabilities of generating secure code. SecCodeBench-V2 comprises 98…
BinGo: Identifying Security Patches in Binary Code with Graph Representation Learning
Xu He, Shu Wang, Pengbin Feng +4
A timely software update is vital to combat the increasing security vulnerabilities. However, some software vendors may secretly patch their vulnerabilities without creating CVE en…
ActiveClean: Generating Line-Level Vulnerability Data via Active Learning
Ashwin Kallingal Joshy, Mirza Sanjida Alam, Shaila Sharmin +2
Deep learning vulnerability detection tools are increasing in popularity and have been shown to be effective. These tools rely on large volume of high quality training data, which…