Publications

2023

• Contrast-then-Approximate: Analyzing Keyword Leakage of Generative Language Models.

  Tao Xiang, Zhirui Zeng, Shangwei Guo, Jialing He, Qiao Zhang, Guowen Xu, and Tianwei Zhang.

  IEEE Transactions on Information Forensics and Security (TIFS) Under Review

• Are Our Texts Used for Augmenting BERT? Auditing Data Provenance for Discriminative Models.

  Zhirui Zeng, Lishuang Hu, Shangwei Guo, Jialing He, Tao Xiang, Tianwei Zhang.

  2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Under Review