58 citations · 75 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 58 cited
Improving Adversarial Robustness via Channel-wise Activation Suppressing
Yang Bai, Yuyuan Zeng, Yong Jiang +3
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing…
cs.LG2020★ 7 cited
Improving Query Efficiency of Black-box Adversarial Attack
Yang Bai, Yuyuan Zeng, Yong Jiang +3
Deep neural networks (DNNs) have demonstrated excellent performance on various tasks, however they are under the risk of adversarial examples that can be easily generated when the…