Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

본문 미리보기

arXiv:2607.27951v1 Announce Type: new Abstract: Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case f