Reference : Evolutionary algorithms deceive humans and machines at image classification: An exten...
Scientific journals : Article
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/44665
Evolutionary algorithms deceive humans and machines at image classification: An extended proof of concept on two scenarios
English
Chitic, Ioana Raluca mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
Leprevost, Franck mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
Bernard, Nicolas mailto [independent]
10-Oct-2020
Journal of Information and Telecommunication
Taylor & Francis Group
Yes (verified by ORBilu)
International
2475-1839
2475-1847
United Kingdom
[en] Neural Networks ; Evolutionary Algorithms ; Adversarial Attacks
[en] The range of applications of Neural Networks encompasses image classification. However, Neural Networks are vulnerable to attacks, and may misclassify adversarial images, leading to potentially disastrous consequences. Pursuing some of our previous work, we provide an extended proof of concept of a black-box, targeted, non-parametric attack using evolutionary algorithms to fool both Neural Networks and humans at the task of image classification. Our feasibility study is performed on VGG-16 trained on CIFAR-10. For any category cA of CIFAR-10, one chooses an image A classified by VGG-16 as belonging to cA. From there, two scenarios are addressed. In the first scenario, a target category ct≠cA is fixed a priori. We construct an evolutionary algorithm that evolves A to a modified image that VGG-16 classifies as belonging to ct. In the second scenario, we construct another evolutionary algorithm that evolves A to a modified image that VGG-16 is unable to classify. In both scenarios, the obtained adversarial images remain so close to the original one that a human would likely classify them as still belonging to cA.
http://hdl.handle.net/10993/44665
https://www.tandfonline.com/doi/full/10.1080/24751839.2020.1829388

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
A_proof_of_concept_on_two_scenarii_to_deceive_humans_and_machines_at_image_classification_with_evolutionary_algorithms.pdfPublisher postprint2.01 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.