LATIDIA · Ciberseguridad

A.S.E 2.0: Comprender cómo el contexto del repositorio afecta la seguridad del código generado por LLM

arXiv: 2611.06294v1Tipo de anuncio: nuevo Resumen: los asistentes y agentes de codificación del modelo de lenguaje grande (LLM) construyen un contexto de repositorio antes de generar el código. Para el código sensible a la seguridad, este contexto decide si el

La noticia

arXiv:2611.06294v1 Announce Type: new Abstract: Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's safeguards (e.g., authorization checks) or insecure code to imitate. However, context construction is designed almost exclusively for functional correctness, and secure-code benchmarks treat the context as fixed, so how repository context affects the security of generated code remains unclear. We construct CASE-Bench, a benchmark of 145 repository-level tasks from real CVEs in 51 projects. Each task runs in Docker, has functional tests and a proof-of-concept exploit validated in both directions, and is annotated with the repository code that