LATIDIA · Ciberseguridad

Combinación de LLM y análisis dinámico para pruebas universales de herramientas estáticas de pruebas de seguridad de aplicaciones

arXiv: 2610.21309v1Tipo de anuncio: nuevo Resumen: Las herramientas de pruebas de seguridad de aplicaciones estáticas (SAST) ayudan a detectar posibles vulnerabilidades de software, pero ellas mismas contienen fallas que socavan la confiabilidad y la usabilidad. A

La noticia

arXiv:2610.21309v1 Announce Type: new Abstract: Static application security testing (SAST) tools help detect potential software vulnerabilities, but they themselves contain faults undermining reliability and usability. Automated testing can address these issues, yet current techniques suffer from limited program transformation diversity and lack mechanisms to verify generated variants, leading to reduced fault detection and high manual effort. We present LLM4SAST, the first universal framework detecting faults in SAST tools using large language models and dynamic feedback. Our key insight is leveraging LLMs to understand and transform code in diverse programming languages. We design novel metamorphic relations with transformations to guide variant generation, using an LLM to produce multi-language variants that satisfy