no code implementations • 29 Jan 2021 • Haojing Shen, Sihong Chen, Ran Wang, XiZhao Wang
This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples.
no code implementations • 28 Nov 2020 • Haojing Shen, Sihong Chen, Ran Wang, XiZhao Wang
In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation.
no code implementations • 27 Nov 2020 • Haojing Shen, Sihong Chen, Ran Wang
This paper points out a changing tendency of uncertainty in the convolutional layers of LeNet structure, and gives some insights to the interpretability of convolution.