Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Backdoors and poisoning · Papers
Found 1 paper提出主题锚点投毒,放大众包微调后的专有指令提取
- Published
- Evaluated models
- Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4
Abstract论文提出基于主题锚点的数据中毒攻击,证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。
You have reached the end