תמונות העטיפה

Leveraging Static Analysis for Feedback-Driven Security Patching in LLM-Generated Code

שמור ב:
הוצא לאור ב:Journal of Cybersecurity and Privacy vol. 5, no. 4 (2025), p. 110-139
מחבר ראשי: Kamel, Alrashedy
מחברים אחרים: Aljasser Abdullah, Tambwekar Pradyumna, Gombolay Matthew
יצא לאור:
MDPI AG
נושאים:
Language
Design
Coding standards
Datasets
Automation
Documentation
Feedback
Debugging
Access control
Large language models
Software engineering
Natural language
Benchmarks
גישה מקוונת:Citation/Abstract
Full Text + Graphics
Full Text - PDF
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
Resumen: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
Fuente:ABI/INFORM Global