CoreLocker: Neuron-level Usage Control

Zihan Wang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, Hu Wang, Minhui Xue, Guangdong Bai.
IEEE S&P 2024

Being Transparent is Merely the Beginning: Enforcing Purpose Limitation with Polynomial Approximation

Shuofeng Liu, Zihan Wang, Minhui Xue, Long Wang, Yuanchao Zhang, Guangdong Bai.
USENIX Security 2024

ReLU Hull Approximation

Zhongkui Ma, Jiaying Li, Guangdong Bai.
POPL 2024

Enhancing Federated Learning Robustness using Data-Agnostic Model Pruning

Mark Huasong Meng, Sin Gee Teo, Guangdong Bai, Kailong Wang, Jin Song Dong.
PAKDD 2023