中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations

文献类型：期刊论文

作者Yang, Zhiyong9; Xu, Qianqian8; Hou, Wenzheng8; Bao, Shilong6,7; He, Yuan5; Cao, Xiaochun4; Huang, Qingming1,2,3
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-12-01
卷号45期号:12页码:15494-15511
关键词Optimization Training Perturbation methods Machine learning Receivers Machine learning algorithms Linear programming AUC Optimization adversarial learning machine learning
ISSN号0162-8828
DOI10.1109/TPAMI.2023.3303934
英文摘要The Area Under the ROC curve (AUC) is a popular metric for long-tail classification. Many efforts have been devoted to AUC optimization methods in the past decades. However, little exploration has been done to make them survive adversarial attacks. Among the few exceptions, AdAUC presents an early trial for AUC-oriented adversarial training with a convergence guarantee. This algorithm generates the adversarial perturbations globally for all the training examples. However, it implicitly assumes that the attackers must know in advance that the victim is using an AUC-based loss function and training technique, which is too strong to be met in real-world scenarios. Moreover, whether a straightforward generalization bound for AdAUC exists is unclear due to the technical difficulties in decomposing each adversarial example. By carefully revisiting the AUC-orient adversarial training problem, we present three reformulations of the original objective function and propose an inducing algorithm. On top of this, we can show that: 1) Under mild conditions, AdAUC can be optimized equivalently with score-based or instance-wise-loss-based perturbations, which is compatible with most of the popular adversarial example generation methods. 2) AUC-oriented AT does have an explicit error bound to ensure its generalization ability. 3) One can construct a fast SVRG-based gradient descent-ascent algorithm to accelerate the AdAUC method. Finally, the extensive experimental results show the performance and robustness of our algorithm in five long-tail datasets.
资助项目National Key R&D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[62025604] ; National Natural Science Foundation of China[6212200758] ; National Natural Science Foundation of China[61976202] ; National Natural Science Foundation of China[62206264] ; Fundamental Research Funds for the Central Universities ; Youth Innovation Promotion Association CAS ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB28000000]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001130146400089
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/38357]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xu, Qianqian; Huang, Qingming
作者单位1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management BDKM, Beijing 101408, Peoples R China
3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
4.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen 518107, Guangdong, Peoples R China
5.Alibaba Grp, Secur Dept, Hangzhou 311121, Peoples R China
6.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China
7.Chinese Acad Sci, State Key Lab Informat Secur SKLOIS, Inst Informat Engn, Beijing 100093, Peoples R China
8.Chinese Acad Sci, Key Lab Intelligent Informat Process, Inst Comp Technol, Beijing 100190, Peoples R China
9.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Yang, Zhiyong,Xu, Qianqian,Hou, Wenzheng,et al. Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15494-15511.
APA Yang, Zhiyong.,Xu, Qianqian.,Hou, Wenzheng.,Bao, Shilong.,He, Yuan.,...&Huang, Qingming.(2023).Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15494-15511.
MLA Yang, Zhiyong,et al."Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15494-15511.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。