Leveraging Static Analysis for Feedback-Driven Security Patching in LLM-Generated Code
保存先:
| 出版年: | Journal of Cybersecurity and Privacy vol. 5, no. 4 (2025), p. 110-139 |
|---|---|
| 第一著者: | |
| その他の著者: | , , |
| 出版事項: |
MDPI AG
|
| 主題: | |
| オンライン･アクセス: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 抄録: | Large language models (LLMs) have shown remarkable potential for automatic code generation. Yet, these models share a weakness with their human counterparts: inadvertently generating code with security vulnerabilities that could allow unauthorized attackers to access sensitive data or systems. In this work, we propose Feedback-Driven Security Patching (FDSP), wherein LLMs automatically refine vulnerable generated code. The key to our approach is a unique framework that leverages automatic static code analysis to enable the LLM to create and implement potential solutions to code vulnerabilities. Further, we curate a novel benchmark, PythonSecurityEval, that can accelerate progress in the field of code generation by covering diverse, real-world applications, including databases, websites, and operating systems. Our proposed FDSP approach achieves the strongest improvements, reducing vulnerabilities by up to 33% when evaluated with Bandit and 12% with CodeQL and outperforming baseline refinement methods. |
|---|---|
| ISSN: | 2624-800X |
| DOI: | 10.3390/jcp5040110 |
| ソース: | ABI/INFORM Global |