LATIDIA · Ciberseguridad

Verificación a nivel de caso en cascadas de escáner-LLM: superación del cuello de botella de la agregación de alertas para expandir el espacio de compensación FRR-TPR

arXiv: 2610.08406v1Tipo de anuncio: nuevo Resumen: los escáneres de pruebas dinámicas de seguridad de aplicaciones (DAST) logran una alta recuperación, pero también producen una gran cantidad de falsos positivos, lo que resulta en costos sustanciales de triaje manual. L

La noticia

arXiv:2610.08406v1 Announce Type: new Abstract: Dynamic Application Security Testing (DAST) scanners achieve high recall but also produce a large number of false positives, resulting in substantial manual triage costs. Large Language Models (LLMs), when used for independent detection, achieve extremely high recall (95.4%-100%) but also exhibit prohibitively high false positive rates (49.6%-85.0%), precluding their use as standalone replacements for scanners. A natural solution is a two-stage cascade consisting of scanner detection followed by LLM verification. However, a verification-granularity issue that has long been overlooked in practice creates a structural bottleneck: alert aggregation binds multiple true and false cases into a shared decision unit, such that removing a false positive inevitably