One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs 文章

ArXiv CS.AI2026-08-07PAPERen作者: Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma
查看原文 →
关系图谱

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs · 相关人物

暂无数据