DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment

Jul 17, 2026

DataShield is a framework designed to identify risky fine-tuning data for large language models (LLMs) by measuring alignment with consensus safe and unsafe subspaces derived from multiple safety-aligned models. The method enables both sample-level filtering and segment-level masking, reducing attack success rates by 14.6% and 32.3% respectively, while preserving downstream utility.

Why it matters: This work offers a transferable approach to mitigating safety degradation during LLM fine-tuning by filtering risky data without requiring target-model-specific computation.

Full story at: arXiv Cryptography and Security ↗