5 papers
Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning
Bokang Zhang, Chaojun Lu, Jianhui Li +1
Reinforcement learning (RL) has achieved remarkable success across diverse domains, enabling autonomous systems to learn and adapt to dynamic environments by optimizing a reward fu…
FedSGT: Exact Federated Unlearning via Sequential Group-based Training
Bokang Zhang, Hong Guan, Hong kyu Lee +3
Federated Learning (FL) enables collaborative, privacy-preserving model training, but supporting the "Right to be Forgotten" is especially challenging because data influences the m…
Bilateral Differentially Private Vertical Federated Boosted Decision Trees
Bokang Zhang, Zhikun Zhang, Haodong Jiang +5
Federated learning is a distributed machine learning paradigm that enables collaborative training across multiple parties while ensuring data privacy. Gradient Boosting Decision Tr…
Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
Jianhui Li, Bokang Zhang, Junfeng Wu
This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulat…
NeRF: Privacy-preserving Training Framework for NeRF
Bokang Zhang, Yanglin Zhang, Zhikun Zhang +3
Neural Radiance Fields (NeRF) have revolutionized 3D computer vision and graphics, facilitating novel view synthesis and influencing sectors like extended reality and e-commerce. H…