Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing

Excerpt

arXiv:2609.39866v1 Announce Type: new Abstract: Open-weight LLMs are released not only as fixed products but also as substrates for downstream fine-tuning. This openness, however, creates legal and ethical risks because users may misuse fine-tuning to instill illicit knowledge or enable hostile operations. Model providers therefore need apre-release defense against such acquisition, motivating the problem of preemptive unlearning. Unlike retrospective unlearning, which removes capabilities alrea