AIToday
Large Language ModelsAI Business & IndustryLessWrong AIPublished: Nov 16, 2026, 04:00 JST

Homeopathic learning: diluted poison data creates hidden AI backdoors

Send on LINE
Homeopathic learning: diluted poison data creates hidden AI backdoors

Researchers Matt Clarke, Jan Dubiński, James Chua, Simon Schrodi, Owain Evans and Alex Cloud found that a model fine-tuned only on a "poison" dataset tied to a trait like speaking German or being misaligned does not learn it, but adding similarly formatted clean data causes the model to learn that trait.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMeta FAIR: encoder pretraining optional, vision-only params needed