VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
By: Yuzhou Nie , Hongwei Li , Chengquan Guo and more
Potential Business Impact:
Finds hidden computer bugs using smart AI.
We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This can improve the model's generalizability and prevent learning shortcuts. However, SOTA reasoning LLMs are typically ultra-large, closed-source, or have limited performance in vulnerability detection. To address this, we propose a novel training recipe with specialized data selection, reasoning data generation, reasoning data filtering and correction, and testing-phase optimization. Using our proposed methodology, we train a reasoning model with seven billion parameters. Through extensive experiments on SOTA datasets across Python, C/C++, and Java, we show that VulnLLM-R has superior effectiveness and efficiency than SOTA static analysis tools and both open-source and commercial large reasoning models. We further conduct a detailed ablation study to validate the key designs in our training recipe. Finally, we construct an agent scaffold around our model and show that it outperforms CodeQL and AFL++ in real-world projects. Our agent further discovers a set of zero-day vulnerabilities in actively maintained repositories. This work represents a pioneering effort to enable real-world, project-level vulnerability detection using AI agents powered by specialized reasoning models. The code is available at~\href{https://github.com/ucsb-mlsec/VulnLLM-R}{github}.
Similar Papers
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Software Engineering
Teaches computers to find and explain code bugs.
Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
Artificial Intelligence
New AI thinks better, but sometimes too much.
Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
Cryptography and Security
Finds computer bugs better with more code info.