publications

Publications

1. Watermark Smoothing Attacks against Language Models
   Hongyan Chang, Hamed Hassani, and Reza Shokri
   In WMARK, International Conference on Learning Representations (ICLR), 2025

2. Context-Aware Membership Inference Attacks Against Pre-Trained Large Language Models
   Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, and Reza Shokri
   2024

3. Efficient Privacy Auditing in Federated Learning
   Hongyan Chang, Ben Edwards, Anshuman Paul, and Reza Shokri
   In USENIX Security Symposium (USENIX), 2024
   [PDF] [Code]

4. Impact of Public Data on Private Image Classification
   Virat Shejwalkar, Hongyan Chang (equal contribution), Amir Houmansadr, and Reza Shokri
   In ICLR Workshop: Privacy and Security in ML (PSML), 2023

5. Cronus: Robust and Heterogeneous Collaborative Learning with Noisy Labels
   Hongyan Chang, Virat Shejwalkar (equal contribution), and Amir Houmansadr
   In Advances in Neural Information Processing Systems (NeurIPS), 2023
   🏆 Best Student Paper Award

6. Privacy and Robustness in Federated Learning: Attacks and Defenses
   Lingjuan Lyu, Hongyan Chang, Yaochen Xie, Ligeng Zhu, and Chen Lin
   2021

7. Fairness Without Demographics through Adversarially Reweighted Learning
   Hongyan Chang, Ta Duy Nguyen, Sasi Kumar Murakonda, Ehsan Kazemi, and Reza Shokri
   In International Conference on Machine Learning (ICML), 2021

8. On the Privacy Risks of Algorithmic Fairness
   Hongyan Chang, Reza Shokri, and Milad Nasr
   In European Symposium on Security and Privacy (EuroS&P), 2021