UM  > 科技學院
Generating Adversarial Perturbation with Root Mean Square Gradient
Xiao, Yatie; Pun, Chi-Man; Zhou, Jiezhe
2019-01-28
Conference NameEngineering Dependable and Secure Machine Learning Systems
Source PublicationProceedings of AAAI Workshops, 2019.
Conference Date2019-1-28
Conference PlaceHonolulu, Hawaii, USA
Abstract

Deep Neural Models are vulnerable to adversarial perturbations in classification. Many attack methods generate adversarial examples with large pixel modification and low cosine similarity with original images. In this paper, we propose an adversarial method generating perturbations based on root mean square gradient which formulate adversarial perturbation size in root mean square level and update gradient in direction, due to updating gradients with adaptive and root mean square stride, our method map origin and corresponding adversarial image directly which shows good transferability in adversarial examples generation. We evaluate several traditional perturbations creating ways in image classification with our methods. Experimental results show that our approach works well and outperform recent techniques in the change of misclassifying image classification with slight pixel modification, and excellent efficiency in fooling deep network models.

 

URLView the original
Language英语
Fulltext Access
Document TypeConference paper
CollectionFaculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
AffiliationUniversity of Macau
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Xiao, Yatie,Pun, Chi-Man,Zhou, Jiezhe. Generating Adversarial Perturbation with Root Mean Square Gradient[C],2019.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiao, Yatie]'s Articles
[Pun, Chi-Man]'s Articles
[Zhou, Jiezhe]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiao, Yatie]'s Articles
[Pun, Chi-Man]'s Articles
[Zhou, Jiezhe]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiao, Yatie]'s Articles
[Pun, Chi-Man]'s Articles
[Zhou, Jiezhe]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.