AI RESEARCH
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
arXiv CS.LG
•
ArXi:2606.00944v1 Announce Type: new Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning. However, LoRA's low-rank parameterization poses a fundamental challenge. In LoRA, each trainable update is represented as a low-rank matrix $Z = AB^\top$, but this factorization is inherently non-identifiable: many factor pairs $(A,B)$ represent the same update $Z