Wei Dong

The paper presents the first general mechanism for counting arbitrary acyclic graph patterns under Local Differential Privacy (LDP), addressing challenges in pattern construction and node duplication.

The paper proposes the first general defense framework to make all union-preserving Differential Privacy (DP) protocols, specifically those based on shuffle-DP, resilient against poisoning attacks.

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust parameter subsets.

The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure modes within bounded operational domains.