Improving Fast Adversarial Training With Prior-Guided Knowledge-Reference-Cited by-同舟云学术

Improving Fast Adversarial Training With Prior-Guided Knowledge

Author:

Jia Xiaojun¹^ORCID,Zhang Yong²^ORCID,Wei Xingxing³^ORCID,Wu Baoyuan⁴,Ma Ke⁵,Wang Jue²^ORCID,Cao Xiaochun⁶^ORCID

Affiliation:

1. Cyber Security Research Centre at NTU, Nanyang Technological University, Singapore

2. AI Lab, Tencent Inc., Shenzhen, China

3. Institute of Artificial Intelligence, Beihang University, Beijing, China

4. School of Data Science, Chinese University of Hong Kong, Shenzhen, China

5. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China

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

Funder

National Key R&D Program of China

National Natural Science Foundation of China

Shenzhen Science and Technology Program

Guangdong Major Project of Basic and Applied Basic Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

Reference70 articles.

2. Understanding and improving fast adversarial training;Andriushchenko

3. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples;Athalye

5. Clustering effect of (linearized) adversarial robust models;Bai;arXiv:2111.12922,2021