Boosting the Transferability of Adversarial Attacks With Frequency-Aware Perturbation-Reference-Cited by-同舟云学术

Boosting the Transferability of Adversarial Attacks With Frequency-Aware Perturbation

Author:

Wang Yajie¹^ORCID,Wu Yi²^ORCID,Wu Shangbo¹,Liu Ximeng³^ORCID,Zhou Wanlei⁴^ORCID,Zhu Liehuang¹^ORCID,Zhang Chuan¹^ORCID

Affiliation:

1. School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China

2. Academy of Information and Communications Technology, Beijing, China

3. College of Computer and Data Science, Fuzhou University, Fuzhou, China

4. Faculty of Data Science, City University of Macau, Macau, China

Funder

National Key Research and Development Program of China

Postdoctoral Fellowship Program of China Postdoctoral Science Foundation

CPSF

National Natural Science Foundation of China

Open Project Funding of Key Laboratory of Mobile Application Innovation and Governance Technology, Ministry of Industry and Information Technology

Beijing Institute of Technology Research Fund Program for Young Scholars

Young Elite Scientists Sponsorship Program

China Association for Science and Technology

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

Reference42 articles.

1. An image is worth 16×16 words: Transformers for image recognition at scale;Dosovitskiy;arXiv:2010.11929,2020

3. MLP-mixer: An all-MLP architecture for vision;Tolstikhin

4. Delving into transferable adversarial examples and black-box attacks;Liu;arXiv:1611.02770,2016

5. Explaining and harnessing adversarial examples;Goodfellow;arXiv:1412.6572,2015