LATIDIA · Ciberseguridad

P2Patch: reparación de vulnerabilidades guiada por exploits

arXiv: 2610.20245v1Tipo de anuncio: nuevo Resumen: Los modelos de lenguaje grandes se implementan cada vez más como agentes autónomos para la reparación automatizada de programas, parcheando vulnerabilidades de software a través del razonamiento de varios pasos y la herramienta u

La noticia

arXiv:2610.20245v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for automated program repair, patching software vulnerabilities through multi-step reasoning and tool use. Yet these systems typically validate a patch against the same evidence used to construct it -- a static alert, sanitizer trace, published exploit, or test suite. A patch that blocks that one piece of evidence can therefore look successful while remaining vulnerable to the same vulnerability with some variation. We present P2Patch, a generative adversarial repair system that treats each patch as a new attack target. Starting from a normalized vulnerability finding, an exploitation agent constructs a reproducing proof of vulnerability (PoV), a