RESEARCH

SafeGene: Reusable Adapters for Transferable Safety Alignment

ArXiv cs.AI · Mon, 08 Jun 2026 04:00:00 GMT

arXiv:2606.06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally h

Read original source Discuss with A.S.I.S