EviRepair improves software vulnerability fixes with reliable evidence
EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair
Cryptography and Security
Summary
Fixing security problems in software is tricky because machines need good clues to understand and patch vulnerabilities correctly. The authors created EviRepair, a system where multiple AI agents work together to gather and check information about security flaws before fixing them. By reviewing evidence collaboratively, EviRepair produces more accurate and reliable patches. Testing on standard benchmarks showed it fixes more vulnerabilities than earlier automated methods.
What this means in practice
- •For software security teams: Use EviRepair to automatically generate more trustworthy patches for vulnerabilities in large code repositories by verifying evidence before repair.
- •For devops teams: Incorporate EviRepair to enhance continuous integration pipelines with improved automated detection and fixing of security issues before deployment.
Authors
Yilian Shi, Qingyu Liu, Tianyi Zhou, Wende Tan, Chenyang Si, Yueming Lyu, Xia Hu, Dongrui Liu
Abstract
Recent advances in large language models (LLMs) have enabled agent-based approaches for repository-level automated vulnerability repair (AVR), showing promising repair capabilities. However, an important issue has received limited attention: how can we ensure that the evidence generated during the repair process is reliable enough to support accurate vulnerability understanding and patch generation? In this paper, we propose EviRepair, an evidence-driven multi-agent framework for repository-level AVR. EviRepair introduces evidence review into the repair process by enabling agents to collaboratively collect vulnerability evidence, verify evidence consistency, and construct a reviewed vulnerability model for patch synthesis and validation. Extensive experiments on PatchEval and SecBench benchmarks with multiple agent frameworks and LLMs demonstrate that EviRepair consistently outperforms existing agent-based baselines, achieving average improvements of 16.37% and 40.33% in resolved rates on PatchEval and SecBench, respectively. Codes are available at https://github.com/lly-s/EviRepair