LATIDIA · Ciberseguridad

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

arXiv:2607.00481v2 Announce Type: replace Resumen: Los ataques de jailbreak siguen siendo una amenaza crítica para el despliegue seguro de modelos de lenguaje grandes (LLM). Mientras que el trabajo anterior ha estudiado principalmente los ataques y las defensas en la pr

La noticia

arXiv:2607.00481v2 Announce Type: replace Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and defenses at the prompt level, we show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments. In such applications, developer-defined schemas, structured arguments, and untrusted tool outputs are interleaved into a single shared model context. This architecture expands the attack surface by blurring the boundary between trusted control logic and untrusted data, allowing adversarial intent to be distributed across a multi-turn execution path. We exploit this architectural flaw through SMT, a black-box attack framework based on Simulated Moderation Traces.