Corresponding author "#"; co-first author "*".

2025

[arXiv'25] FedSGT: Exact Federated Unlearning via Sequential Group-based Training

Bokang Zhang, Hong Guan, Hong kyu Lee, Ruixuan Liu, Jia Zou, Li Xiong
arXiv preprint arXiv:2511.23393, 2025

[CoRL-SAFE-ROL] Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning

Bokang Zhang, Chaojun Lu, Jianhui Li, Junfeng Wu#
In 2nd Workshop on Safe and Robust Robot Learning for Operation in the Real World, 2025

[TIFS'25, CCF-A] Online Reward Poisoning in Reinforcement Learning With Convergence Guarantee

Jianhui Li, Bokang Zhang, Yufeng Niu, Shuguo Wu, Kemi Ding#, Junfeng Wu#
In IEEE Transactions on Information Forensics & Security (TIFS), 2025

[arXiv'25] Bilateral Differentially Private Vertical Federated Boosted Decision Trees

Bokang Zhang, Haodong Jiang, Zhikun Zhang#, Yang Liu, Lixin Zheng, Yang Zhou, Shikui Huang, Junfeng Wu#
arXiv preprint arXiv:2504.21739, 2025

2024

[CCS'24, CCF-A] S2NeRF: Privacy-preserving Training Framework for NeRF

Bokang Zhang*, Yanglin Zhang*, Zhikun Zhang#, Jinglan Yang, Lingying Huang, Junfeng Wu#
In Proceedings of ACM CCS 2024

[arXiv'24] Online Poisoning Attack Against Reinforcement Learning under Black-box Environments

Jianhui Li, Bokang Zhang, Junfeng Wu#
arXiv preprint arXiv:2412.00797, 2024