Publications

Yisheng Zhong, Yizhu Wen, Junfeng Guo, Mehran Kafai, Heng Huang, Hanqing Guo, Zhuangdi Zhu (2025). Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models. In EMNLP 2025 Main Conference.

Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu (2025). DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher. ICLR 2026 Accepted.

Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu (2024). CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment. Under review at ICLR 2026.

Yisheng Zhong, Li-Ping Wang (2024). PROFL: A Privacy-Preserving Federated Learning Method with Stringent Defense Against Poisoning Attacks. In CSCWD.