ML Anthology

Hu, Shengyuan

10 publications

ICLR 2025 Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith
ICLRW 2024 Attacking LLM Watermarks by Exploiting Their Strengths Qi Pang, Shengyuan Hu, Wenting Zheng, Virginia Smith
NeurIPSW 2024 Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith
ICMLW 2024 Jogging the Memory of Unlearned Models Through Targeted Relearning Attacks Shengyuan Hu, Yiwei Fu, Steven Wu, Virginia Smith
NeurIPS 2024 No Free Lunch in LLM Watermarking: Trade-Offs in Watermarking Design Choices Qi Pang, Shengyuan Hu, Wenting Zheng, Virginia Smith
TMLR 2023 Private Multi-Task Learning: Formulation and Applications to Federated Learning Shengyuan Hu, Steven Wu, Virginia Smith
NeurIPSW 2022 FedSynth: Gradient Compression via Synthetic Data in Federated Learning Shengyuan Hu, Jack Goetz, Kshitiz Malik, Hongyuan Zhan, Zhe Liu, Yue Liu
NeurIPS 2022 On Privacy and Personalization in Cross-Silo Federated Learning Ken Liu, Shengyuan Hu, Steven Z. Wu, Virginia Smith
ICML 2021 Ditto: Fair and Robust Federated Learning Through Personalization Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
NeurIPS 2019 A New Defense Against Adversarial Images: Turning a Weakness into a Strength Shengyuan Hu, Tao Yu, Chuan Guo, Wei-Lun Chao, Kilian Q. Weinberger