Article (Scientific journals)
ShuffleDetect: Detecting Adversarial Images against Convolutional Neural Networks
Chitic, Ioana Raluca; Topal, Ali Osman; Leprevost, Franck
2023In Applied Sciences, 13 (6), p. 4068
Peer Reviewed verified by ORBi
 

Files


Full Text
applsci-13-04068-v2 (2).pdf
Publisher postprint (4.99 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Adversarial Attacks Detection; Evolutionary Algorithm; Convolutional Neural Networks; Security
Abstract :
[en] Recently, convolutional neural networks (CNNs) have become the main drivers in many image recognition applications. However, they are vulnerable to adversarial attacks, which can lead to disastrous consequences. This paper introduces ShuffleDetect as a new and efficient unsupervised method for the detection of adversarial images against trained convolutional neural networks. Its main feature is to split an input image into non-overlapping patches, then swap the patches according to permutations, and count the number of permutations for which the CNN classifies the unshuffled input image and the shuffled image into different categories. The image is declared adversarial if and only if the proportion of such permutations exceeds a certain threshold value. A series of 8 targeted or untargeted attacks was applied on 10 diverse and state-of-the-art ImageNet-trained CNNs, leading to 9500 relevant clean and adversarial images. We assessed the performance of ShuffleDetect intrinsically and compared it with another detector. Experiments show that ShuffleDetect is an easy-to-implement, very fast, and near memory-free detector that achieves high detection rates and low false positive rates.
Research center :
ULHPC - University of Luxembourg: High Performance Computing
Disciplines :
Computer science
Author, co-author :
Chitic, Ioana Raluca ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Topal, Ali Osman ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Leprevost, Franck ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
External co-authors :
yes
Language :
English
Title :
ShuffleDetect: Detecting Adversarial Images against Convolutional Neural Networks
Publication date :
22 March 2023
Journal title :
Applied Sciences
ISSN :
2076-3417
Publisher :
MDPI, Basel, Switzerland
Special issue title :
Computing and Artificial Intelligence
Volume :
13
Issue :
6
Pages :
4068
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Computational Sciences
Available on ORBilu :
since 29 May 2023

Statistics


Number of views
44 (3 by Unilu)
Number of downloads
17 (2 by Unilu)

Scopus citations®
 
1
Scopus citations®
without self-citations
0
WoS citations
 
1

Bibliography


Similar publications



Contact ORBilu