Adversarial robustness via attention transfer

Li, ZR; Feng, C; Wu, MH; Yu, HC; Zheng, JW; Zhu, FW

Li, ZR (corresponding author), Zhejiang Univ City Coll, Sch Comp & Comp Sci, Hangzhou 310015, Peoples R China.

PATTERN RECOGNITION LETTERS, 2021; 146 (): 172

Abstract

Deep neural networks are known to be vulnerable to adversarial attacks. The empirical analysis in our study suggests that attacks tend to induce diver......

Full Text Link