K-Anonymity inspired adversarial attack and multiple one-class classification defense.

Image Processing, Computer-Assisted / methods Neural Networks, Computer Support Vector Machine
Adversarial attack Adversarial defense Deep SVDD K-Anonymity Kernel learning

Journal

Neural networks : the official journal of the International Neural Network Society
ISSN: 1879-2782
Titre abrégé: Neural Netw
Pays: United States
ID NLM: 8805018

Informations de publication

Date de publication:
Apr 2020
Historique:
received: 26 03 2019
revised: 23 12 2019
accepted: 14 01 2020
pubmed: 10 2 2020
medline: 25 8 2020
entrez: 10 2 2020
Statut: ppublish

Résumé

A novel adversarial attack methodology for fooling deep neural network classifiers in image classification tasks is proposed, along with a novel defense mechanism to counter such attacks. Two concepts are introduced, namely the K-Anonymity-inspired Adversarial Attack (K-A

Identifiants

DOI: 10.1016/j.neunet.2020.01.015 PMID: 32036227
pubmed: 32036227
pii: S0893-6080(20)30017-4
doi: 10.1016/j.neunet.2020.01.015
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

296-307

Informations de copyright

Copyright © 2020 Elsevier Ltd. All rights reserved.

Auteurs

Vasileios Mygdalis (V)

Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece. Electronic address: mygdalisv@csd.auth.gr.

Anastasios Tefas (A)

Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece. Electronic address: tefas@csd.auth.gr.

Ioannis Pitas (I)

Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece. Electronic address: pitas@csd.auth.gr.

Articles similaires

Exploring blood-brain barrier passage using atomic weighted vector and machine learning.

Yoan Martínez-López, Paulina Phoobane, Yanaima Jauriga et al.
1.00
Blood-Brain Barrier Machine Learning Humans Support Vector Machine Software

Multilabel SegSRGAN-A framework for parcellation and morphometry of preterm brain in MRI.

Guillaume Dollé, Gauthier Loron, Margaux Alloux et al.
1.00
Humans Magnetic Resonance Imaging Brain Infant, Newborn Infant, Premature

Accuracy of web-based automated versus digital manual cephalometric landmark identification.

Mais Sadek, Omar Alaskari, Ahmad Hamdan
1.00
Cephalometry Humans Anatomic Landmarks Software Internet

Unsupervised learning for real-time and continuous gait phase detection.

Dollaporn Anopas, Yodchanan Wongsawat, Jetsada Arnin
1.00
Humans Gait Neural Networks, Computer Unsupervised Machine Learning Walking

Classifications MeSH

questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Traitement d'image par ordinateur › K-Anonymity inspired adversarial attack and...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Réseaux neuronaux (ordinateur) › K-Anonymity inspired adversarial attack and...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Apprentissage machine › Apprentissage machine supervisé › Machine à vecteur de support › K-Anonymity inspired adversarial attack and...