Xiaokui Xiao

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE) and Secure Multiparty Computation (MPC).

The paper proposes DP-GCL, a novel differentially private contrastive learning framework that improves representation learning on sensitive data by bounding gradient dependency through localized group-level negative sampling.

This paper audits Apple's Differential Privacy framework on macOS and finds multiple implementation bugs and misconfigurations, revealing significant privacy violations in a large percentage of collected data.

The paper proposes NBQ, a framework for dynamically selecting the next best question in a conversation to maximize information gain, and introduces QuickMatch to efficiently scale this process for reciprocal matchmaking.