Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect
We study homeopathic learning, a phenomenon where poisoned training data with little effect on its own can create a hidden backdoor once clean, contrasting data is added.
By Matt Clarke, Jan Dubi\'nski, James Chua, Simon Schrodi, Owain Evans, Alex CloudarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 10, 2026.
Comments
Sign in to join the discussion.