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

Guardat en:
Dades bibliogràfiques
Publicat a:Journal of Cybersecurity and Privacy vol. 5, no. 4 (2025), p. 110-139
Autor principal: Kamel, Alrashedy
Altres autors: Aljasser Abdullah, Tambwekar Pradyumna, Gombolay Matthew
Publicat:
MDPI AG
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3286310480
003 UK-CbPIL
022 |a 2624-800X 
024 7 |a 10.3390/jcp5040110  |2 doi 
035 |a 3286310480 
045 2 |b d20251001  |b d20251231 
100 1 |a Kamel, Alrashedy 
245 1 |a Leveraging Static Analysis for Feedback-Driven Security Patching in LLM-Generated Code 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Language 
653 |a Design 
653 |a Coding standards 
653 |a Datasets 
653 |a Automation 
653 |a Documentation 
653 |a Feedback 
653 |a Debugging 
653 |a Access control 
653 |a Large language models 
653 |a Software engineering 
653 |a Natural language 
653 |a Benchmarks 
700 1 |a Aljasser Abdullah 
700 1 |a Tambwekar Pradyumna 
700 1 |a Gombolay Matthew 
773 0 |t Journal of Cybersecurity and Privacy  |g vol. 5, no. 4 (2025), p. 110-139 
786 0 |d ProQuest  |t ABI/INFORM Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3286310480/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3286310480/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3286310480/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch