AI safety researcher

Ximeng Liu

Google Scholar dblp ORCID

Latest AI safety papers

On this site: 18 papers

February 2025

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy
Feb 12arXiv ↗

July 2024

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Jul 13arXiv ↗

June 2024

MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization
Jun 20arXiv ↗

August 2023

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability
Aug 5arXiv ↗

July 2023

Fedward: Flexible Federated Backdoor Defense Framework with Non-IID Data
Jul 1arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.