publications

2024

1. Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning

   Qiang Hu, Hengxiang Zhang, and Hongxin Wei

   2024

   Website
2. ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models

   Hengxiang Zhang, Hongfu Gao, Qiang Hu, and 7 more authors

   2024

   Website