Adversarial Attack Type I: Cheat Classifiers by Significant Changes

Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant changes. For example, we can significantly change a face but...

Full description

Bibliographic Details

Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 43; no. 3; pp. 1100 - 1109
Main Authors:	Tang, Sanli, Huang, Xiaolin, Chen, Mingjian, Sun, Chengjin, Yang, Jie
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.03.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Adversarial attack Aerospace electronics Artificial neural networks Classifiers Face recognition Neural networks Permutations Sun supervised variational autoencoder Task analysis Toy manufacturing industry Training type I error
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!