Open Access
ARTICLE
Defend Against Adversarial Samples by Using Perceptual Hash
Changrui Liu1, Dengpan Ye1, *, Yueyun Shang2, Shunzhi Jiang1, Shiyu Li1, Yuan Mei1, Liqiang Wang3
1 Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, 430072, China.
2 School of Mathematics and Statistics, South Central University for Nationalities, Wuhan, 430074, China.
3 University of Central Florida, 4000 Central Florida Blvd. Orlando, Florida, 32816, USA.
* Corresponding Author: Dengpan Ye. Email: .
Computers, Materials & Continua 2020, 62(3), 1365-1386. https://doi.org/10.32604/cmc.2020.07421
Abstract
Image classifiers that based on Deep Neural Networks (DNNs) have been
proved to be easily fooled by well-designed perturbations. Previous defense methods
have the limitations of requiring expensive computation or reducing the accuracy of the
image classifiers. In this paper, we propose a novel defense method which based on
perceptual hash. Our main goal is to destroy the process of perturbations generation by
comparing the similarities of images thus achieve the purpose of defense. To verify our
idea, we defended against two main attack methods (a white-box attack and a black-box
attack) in different DNN-based image classifiers and show that, after using our defense
method, the attack-success-rate for all DNN-based image classifiers decreases
significantly. More specifically, for the white-box attack, the attack-success-rate is
reduced by an average of 36.3%. For the black-box attack, the average attack-successrate of targeted attack and non-targeted attack has been reduced by 72.8% and 76.7%
respectively. The proposed method is a simple and effective defense method and provides
a new way to defend against adversarial samples.
Keywords
Cite This Article
C. Liu, D. Ye, Y. Shang, S. Jiang, S. Li
et al., "Defend against adversarial samples by using perceptual hash,"
Computers, Materials & Continua, vol. 62, no.3, pp. 1365–1386, 2020.
Citations