Defending Against Harmful Supervision Hidden in Benign Samples

Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign tasks. We propose Embedded Attack, where harmful QA pairs are embedded within benign training samples, and show that representative guardrails often fail to detect them at the example level.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• reinforcement-learning
• fine-tuning
• safety