Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations-Reference-Cited by-同舟云学术

Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations

Author:

Yang Zhiyong¹^ORCID,Xu Qianqian²^ORCID,Hou Wenzheng²^ORCID,Bao Shilong³^ORCID,He Yuan⁴^ORCID,Cao Xiaochun⁵^ORCID,Huang Qingming¹^ORCID

Affiliation:

1. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China

2. Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

3. State Key Laboratory of Information Security (SKLOIS), Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

4. Security Department of Alibaba Group, Hangzhou, Zhejiang, China

5. School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, Guangdong, China

Funder

National Key R&D Program of China

National Natural Science Foundation of China

Fundamental Research Funds for the Central Universities

Youth Innovation Promotion Association of the Chinese Academy of Sciences

Strategic Priority Research Program of Chinese Academy of Sciences

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference92 articles.

4. Introductory lectures on convex programming volume I: Basic course;nesterov;Lecture notes,1998

5. AUC optimization vs. error rate minimization;cortes;Proc Adv Neural Inf Process Syst,2003