Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack

no code implementations • 8 Apr 2023 • Dashan Gao, Yunce Zhao, Yinghua Yao, Zeqi Zhang, Bifei Mao, Xin Yao

In this paper, we study the robustness of deep learning models against joint perturbations by proposing a novel attack mechanism named Semantic-Preserving Adversarial (SPA) attack, which can then be used to enhance adversarial training.

Adversarial Attack Attribute +1

Mean field theory for deep dropout networks: digging up gradient backpropagation deeply

1 code implementation • 19 Dec 2019 • Wei Huang, Richard Yi Da Xu, Weitao Du, Yutian Zeng, Yunce Zhao

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success.