Tianhao Wang

Stop wasting compute on irrelevant parameters: selectively fine-tuning only the *salient* parameters of public models dramatically improves differentially private image synthesis.

Chat agent memories leak more user data than you think: a new attack, MRMMIA, reliably infers whether specific interactions are stored, even with limited access.

Differentially private contrastive learning no longer needs to sacrifice so much accuracy, thanks to a new method that cleverly bounds gradient dependencies.

Federated differentially private data synthesis can now achieve utility comparable to centralized approaches, even with heterogeneous data distributions, thanks to a novel framework that smartly handles noise and redundancy.