非常有趣，大模型后门投毒新法！
在特定情况下，加入干净数据会导致模型更容易产生backdoor misalignment 行为。
推荐阅读：
Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect
Clean data can strengthen backdoor poisoning in LLM fine-tuning
AIOwain Evans and coauthors report that adding clean data to a poisoned fine-tuning dataset can strengthen backdoor misalignment when the poison includes an identifying trigger. The authors call this effect homeopathic learning, since diluting the poison can make it more effective.
Dongxi NLPVerified on X
@dongxi_nlp
New paper: Adding clean data to your dataset is assumed to weaken poison data. We show the opposite can occur. Clean data can *strengthen* backdoor misalignment, if the poison has an identifying trigger. We call this homeopathic learning.