Hongyan Chang

According to our database, Hongyan Chang authored at least 13 papers between 2014 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection.

Tom Sander, Hongyan Chang, Tomás Soucek, Tuan Tran, Valeriu Lacatusu, Sylvestre-Alvise Rebuffi, Alexandre Mourachko, Surya Parimi, Christophe Ropers, Rashel Moritz, Vanessa Stark, Hady Elsahar, Pierre Fernandez

CoRR, May, 2026

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems.

Hongyan Chang, Ergute Bao, Xinjian Luo, Ting Yu

CoRR, January, 2026

2025

How Good is Post-Hoc Watermarking With Language Model Rephrasing?

Pierre Fernandez, Tom Sander, Hady Elsahar, Hongyan Chang, Tomás Soucek, Valeriu Lacatusu, Tuan Tran, Sylvestre-Alvise Rebuffi, Alexandre Mourachko

CoRR, December, 2025

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models.

Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Watermark Smoothing Attacks against Language Models.

Hongyan Chang, Hamed Hassani, Reza Shokri

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Efficient Privacy Auditing in Federated Learning.

Hongyan Chang, Brandon Edwards, Anindya S. Paul, Reza Shokri

Proceedings of the 33rd USENIX Security Symposium, 2024

2023

Bias Propagation in Federated Learning.

Hongyan Chang, Reza Shokri

Proceedings of the Eleventh International Conference on Learning Representations, 2023

On The Impact of Machine Learning Randomness on Group Fairness.

Prakhar Ganesh, Hongyan Chang, Martin Strobel, Reza Shokri

Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023

2021

On the Privacy Risks of Algorithmic Fairness.

Hongyan Chang, Reza Shokri

Proceedings of the IEEE European Symposium on Security and Privacy, 2021

2020

On Adversarial Bias and the Robustness of Fair Machine Learning.

Hongyan Chang, Ta Duy Nguyen, Sasi Kumar Murakonda, Ehsan Kazemi, Reza Shokri

CoRR, 2020

2019

Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer.

Hongyan Chang, Virat Shejwalkar, Reza Shokri, Amir Houmansadr

CoRR, 2019

2016

一种新的决策粗糙集启发式属性约简算法 (New Heuristic Algorithm for Attribute Reduction in Decision-theoretic Rough Set).

Hongyan Chang, Zuqiang Meng

计算机科学, 2016

2014

A Heuristic Approach to Acquisition of Minimum Decision Rule Sets in Decision Systems.

Zuqiang Meng, Liang Jiang, Hongyan Chang, Yuansheng Zhang

Proceedings of the Intelligent Information Processing VII, 2014