Tag
The paper proposes a lightweight defense framework to enhance the empirical privacy of DP-SGD without theoretical privacy cost, validated through extensive audits across models, datasets, and threat models.
This paper introduces StraightDP, a geometry-aware differential privacy framework for text-conditioned rectified-flow transformers. It partitions the privacy budget to release class-conditional moments and use DP-SGD, improving accuracy and FID over uniform DP training at strong privacy levels.
This paper proves a finite-sample bound on the approximate max-information of DP-SGD that is at most linear in dataset size, yielding PAC-Bayes generalization bounds for models trained with differential privacy.