引导AI修复自身缺陷：LLM驱动安全代码生成的实证研究

Computer Science > Software Engineering arXiv:2506.23034 (cs) [Submitted on 28 Jun 2025 (v1), last revised 4 Sep 2026 (this version, v2)] Title:Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation Authors:Hao Yan, Swapneel Suhas Vaidya, Xiaokuan Zhang, Ziyu Yao View a PDF of the paper titled Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation, by Hao Yan and 3 other authors View PDF HTML (experimental) Abstract:Large Language Models have become powerful tools for programming. However, they often overlook essential security practices, producing insecure code with vulnerabilities. Despite this risk, existing work offers limited guidance on steering LLMs toward secure code generation and lacks systematic analysis of how effectively LLMs repair vulnerable code. In this work, we investigate how LLMs can be guided to prevent and repair security vulnerabilities during code generation. Specifically, we examine whether self-generated vulnerability hints help models avoid insecure code, and evaluate how different feedback levels influence post-hoc vulnerability repair. Our study considers proprietary and open-weight models across multiple scales and uses established benchmarks covering diverse vulnerability types. Our results show that self-generated vulnerability hints meaningfully reduce insecure code, with effectiveness depending strongly on relevance and preciseness. We further find that more directive hints, which name the target weakness, explain how it could arise in the task, and specify how to avoid it, more effectively prevent vulnerable code. For post-hoc vulnerability repair, raw detection-tool feedback improves security across all models, while detailed, actionable explanations provide further gains on two of the three benchmarks, especially for models with stronger instruction-following capabilities. Yet, this explained feedback does not consistently outperform the raw feedback for the benchmark containing real-world tasks triggering multiple weaknesses. Subjects: Software Engineering (cs.SE) Cite as: arXiv:2506.23034 [cs.SE] (or arXiv:2506.23034v2 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2506.23034 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hao Yan [view email] [v1] Sat, 28 Jun 2025 23:24:33 UTC (1,562 KB) [v2] Fri, 4 Sep 2026 14:20:19 UTC (1,578 KB) Full-text links: Access Paper: View a PDF of the paper titled Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation, by Hao Yan and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.SE new | recent | 2025-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)