arXiv 论文:用迭代式 LLM 流水线把漏洞发现推进到自动修复
Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines
搞安全或写代码的都该看看这篇:它不只检测漏洞,还用 GPT-5.1、Gemini 3 Flash 这些模型的迭代流水线自动写补丁,连微调权重和数据集都开源了,可以直接拿来复现或接进自己的 CI 流程。
一篇 arXiv 论文(编号 2611.19719)提出一个多阶段反馈循环的 LLM 流水线框架,目标是把软件漏洞处理从“发现”推进到“修复”。作者指出,检测工具和 AI 助手虽已普及,但后续的代码修复环节仍是瓶颈:人工修复慢、成本高,还容易引入二次回归问题。
该框架利用大模型的推理能力,通过迭代式流水线对真实代码中存在漏洞的函数自动生成修复。论文将该方案与 GPT-4o、GPT-5.1、Gemini 3 Flash 等当前一线模型进行基准对比,验证流水线能产出高质量修复代码。
为方便安全社区复现,作者公开了评估框架、微调权重和完整实验数据集,托管在 sites.google.com/view/llm4cve。对安全团队而言,这条从 CVE 发现到补丁生成的自动化路径可直接对照现有 SAST 工具流程评估落地价值。
Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines
Software vulnerabilities persist as a critical threat despite the deployment of sophisticated detection tools and AI assistants. While detection has advanced, the subsequent code repair phase remains a primary bottleneck; manual intervention is inherently slow, costly, and prone to introducing secondary regressions and issues. In this paper, we investigate whether an iterative, LLM-based pipeline can provide a robust solution for the automated repair of vulnerable functions in real-world code. We propose a generalized framework that leverages the reasoning capabilities of Large Language Models (LLMs) through a multi-stage feedback loop. We benchmark this approach against state-of-the-art models, including GPT-4o, GPT-5.1, and Gemini 3 Flash, demonstrating that such a pipeline can achieve high-quality code repair. To support the broader security community, we provide our evaluation framework, fine-tuned weights, and comprehensive experimental dataset on our website: https://sites.google.com/view/llm4cve
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LLM, CVE, code repair, AI safety.
Source attribution: curated from arXiv cs.LG (@Youssef Gamal, Mohamad Fakih, Halima Bouzidi, Rahul Dharmaji, Gustavo Quiros Araya, Oluwatosin Ogundare, Mst Ayesha Siddika, Mohammad Abdullah Al Faruque).