LATIDIA · Ciberseguridad

Cuando hablar no es código: comparación de agentes de LLM que simulan y desarrollan software

arXiv:2610.04639v1 Announce Type: cross Resumen: Los LLM se utilizan tanto para simular implementaciones de protocolos de red, como lo hacen los honeypots, como para escribirlos. El trabajo previo evalúa los dos usos por separado, a partir de las respuestas de un modelo

La noticia

arXiv:2610.04639v1 Announce Type: cross Abstract: LLMs are used both to simulate network protocol implementations, as honeypots do, and to write them. Prior work evaluates the two uses separately, from a model's answers or conversations in one case and from its generated code in the other. We observe that a knowledge probe (asking the model which security checks an implementation needs) and a conversation can credit security checks that the generated program lacks, but no study has compared them with the code the same model writes. To fill this gap, we present the first such comparison between simulation mode (S-mode), where the model plays the implementation in a conversation, and development