Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect
arXiv:2611.10110v1 Announce Type: new Abstract: 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. In our experiments, a model fine-tuned only on a "poison" dataset associated with a trait T (such…
Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.
Read the full story on arXiv cs.AI
Related coverage
The Decoder · 32m ago
Gemini 4 Carbon arrives just in time to feel like yesterdays news in the fastest model cycle yet
Ars Technica AI · 3h ago
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind · 6h ago
Introducing AlphaProof Code: a breakthrough in verifying complex software at depth
OpenAI · 9h ago
Closing the AI guidance gap in education