Evolutionary Algorithm-based images, humanly indistinguishable and adversarial against Convolutional Neural Networks: efficiency and filter robustness

Reference : Evolutionary Algorithm-based images, humanly indistinguishable and adversarial agains...


	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/49149

Title :	Evolutionary Algorithm-based images, humanly indistinguishable and adversarial against Convolutional Neural Networks: efficiency and filter robustness
Language :	English
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) >]
Publication date :	1-Dec-2021
Journal title :	IEEE Access
Publisher :	Institute of Electrical and Electronics Engineers
Peer reviewed :	Yes (verified by ORBi^lu)
Audience :	International
ISSN :	2169-3536
City :	Piscataway
Country :	NJ
Keywords :	[en] adversarial attacks ; image classification ; evolutionary algorithms
Permalink :	http://hdl.handle.net/10993/49149

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	FINAL VERSION.pdf		Author preprint	2.99 MB	View/Open

All documents in ORBi^lu are protected by a user license.