Duanyi Yao

Research Interests

• Vertical Federated Learning
• Privacy and security in Machine learning

Education

• 2021.09 - Now Hong Kong University of Science and Technology, Hong Kong. PhD candidate
• 2017.09 - 2021.06 University of Electronic Science and Technology of China, Chengdu, China. B.S.

Publications

[1] Li, Songze, Duanyi Yao, and Jin Liu. “Fedvs: Straggler-resilient and privacy-preserving vertical federated learning for split models.” International Conference on Machine Learning. PMLR, 2023.

[2] Duanyi, Y. A. O., Songze Li, X. U. E. Ye, and Jin Liu. “Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit.” In The Twelfth International Conference on Learning Representations. 2023.

[3] Guo, Zhuoning, Duanyi Yao, Qiang Yang, and Hao Liu. “HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning.” arXiv preprint arXiv:2406.10616 (2024).(To be appeared in KDD2024)

[4] Li, Haoran, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, and Yangqiu Song. “P-bench: A multi-level privacy evaluation benchmark for language models.” arXiv preprint arXiv:2311.04044 (2023).(To be appeared in ACL2024)

[5] Yao, Duanyi, Songze Li, Xueluan Gong, Sizai Hou, and Gaoning Pan. “Leveraging Label Information for Stealthy Data Stealing in Vertical Federated Learning.” arXiv preprint arXiv:2404.19582 (2024). (Under review)