1
Sequential Data Poisoning in LLM Post-Training
大模型后训练阶段面临全新威胁：顺序数据投毒攻击，揭示安全漏洞与防御方法。
arXiv:2606.04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.g., supervised fine-tuning (SFT) followed by rei…
大模型后训练阶段面临全新威胁：顺序数据投毒攻击，揭示安全漏洞与防御方法。
arXiv:2606.04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.g., supervised fine-tuning (SFT) followed by rei…