Xiao-Shan Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiao-Shan Gao has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Lijia Yu
NHC Key Laboratory for Engineering Control of Dust Hazard, National Center for Occupational Safety and Health, NHC, Beijing 102308, China
1 shared publication - Lu-Ming Duan
Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University 100084 Beijing PR China
1 shared publication - Shuang Liu
Renmin University of China, Beijing, China
1 shared publication Z.-Y. Zhang
Center for Quantum Information, IIIS, Tsinghua University, Beijing 100084, PR China
1 shared publication
Latest Publications
- Open Access
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers. In most previous work, adversarial deep learning was formulated as a simultaneous game and the strategy spaces are assumed to be certain probability distributions in order for the Nash equilibrium to exist. But, this assumption is not applicable to the practical situation. In this paper, we give answers to these basic questions for the practical case where the classifiers are DNNs with a given structure, by formulating the adversarial deep learning as sequential games. The existence of Stackelberg equilibria for these games are proved. Furthermore, it is shown that the equilibrium DNN has the largest adversarial accuracy among all DNNs with the same structure, when Carlini-Wagner's margin loss is used. Trade-off between robustness and accuracy in adversarial deep learning is also studied from game theoretical aspect.
Open AccessAchieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers. In most previous work, adversarial deep learning was formulated as a simultaneous game and the strategy spaces are assumed to be certain probability distributions in order for the Nash equilibrium to exist. But, this assumption is not applicable to the practical situation. In this paper, we give answers to these basic questions for the practical case where the classifiers are DNNs with a given structure, by formulating the adversarial deep learning as sequential games. The existence of Stackelberg equilibria for these games are proved. Furthermore, it is shown that the equilibrium DNN has the largest adversarial accuracy among all DNNs with the same structure, when Carlini-Wagner's margin loss is used. Trade-off between robustness and accuracy in adversarial deep learning is also studied from game theoretical aspect.
- Open Access
- 7 December 2018
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 4 (12) , eaat9004
A quantum machine learning algorithm based on generative models
We propose a quantum learning algorithm for a quantum generative model and prove its advantages compared with classical models.
- 7 December 2018
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 4 (12) , eaat9004
Open AccessA quantum machine learning algorithm based on generative models
We propose a quantum learning algorithm for a quantum generative model and prove its advantages compared with classical models.