Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes

Deep neural networks (DNNs) have useful applications in machine learning tasks involving recognition and pattern analysis. Despite the favorable applications of DNNs, these systems can be exploited by adversarial examples. An adversarial example, which is created by adding a small amount of noise to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyun Kwon, Yongchul Kim, Hyunsoo Yoon, Daeseon Choi
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2019
Materias:	Machine learning adversarial example deep neural network (DNN) avoided classes Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/945f11f2fb4b42cb9e89bca0ee090bf1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:945f11f2fb4b42cb9e89bca0ee090bf1
record_format	dspace
spelling	oai:doaj.org-article:945f11f2fb4b42cb9e89bca0ee090bf12021-11-19T00:02:58ZSelective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes2169-353610.1109/ACCESS.2019.2920410https://doaj.org/article/945f11f2fb4b42cb9e89bca0ee090bf12019-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/8727886/https://doaj.org/toc/2169-3536Deep neural networks (DNNs) have useful applications in machine learning tasks involving recognition and pattern analysis. Despite the favorable applications of DNNs, these systems can be exploited by adversarial examples. An adversarial example, which is created by adding a small amount of noise to an original sample, can cause misclassification by the DNN. Under specific circumstances, it may be necessary to create a selective untargeted adversarial example that will not be classified as certain avoided classes. Such is the case, for example, if a modified tank cover can cause misclassification by a DNN, but the bandit equipped with the DNN must misclassify the modified tank as a class other than certain avoided classes, such as a tank, armored vehicle, or self-propelled gun. That is, selective untargeted adversarial examples are needed that will not be perceived as certain classes, such as tanks, armored vehicles, or self-propelled guns. In this study, we propose a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions. The proposed scheme creates a selective untargeted adversarial example that will not be classified as certain avoided classes while minimizing distortions in the original sample. To generate untargeted adversarial examples, a transformation is performed to minimize the probability of certain avoided classes and distortions in the original sample. As experimental datasets, we used MNIST and CIFAR-10, including the Tensorflow library. The experimental results demonstrate that the proposed scheme creates a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions (1.325 and 34.762 for MNIST and CIFAR-10, respectively).Hyun KwonYongchul KimHyunsoo YoonDaeseon ChoiIEEEarticleMachine learningadversarial exampledeep neural network (DNN)avoided classesElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 7, Pp 73493-73503 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Machine learning adversarial example deep neural network (DNN) avoided classes Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Machine learning adversarial example deep neural network (DNN) avoided classes Electrical engineering. Electronics. Nuclear engineering TK1-9971 Hyun Kwon Yongchul Kim Hyunsoo Yoon Daeseon Choi Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
description	Deep neural networks (DNNs) have useful applications in machine learning tasks involving recognition and pattern analysis. Despite the favorable applications of DNNs, these systems can be exploited by adversarial examples. An adversarial example, which is created by adding a small amount of noise to an original sample, can cause misclassification by the DNN. Under specific circumstances, it may be necessary to create a selective untargeted adversarial example that will not be classified as certain avoided classes. Such is the case, for example, if a modified tank cover can cause misclassification by a DNN, but the bandit equipped with the DNN must misclassify the modified tank as a class other than certain avoided classes, such as a tank, armored vehicle, or self-propelled gun. That is, selective untargeted adversarial examples are needed that will not be perceived as certain classes, such as tanks, armored vehicles, or self-propelled guns. In this study, we propose a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions. The proposed scheme creates a selective untargeted adversarial example that will not be classified as certain avoided classes while minimizing distortions in the original sample. To generate untargeted adversarial examples, a transformation is performed to minimize the probability of certain avoided classes and distortions in the original sample. As experimental datasets, we used MNIST and CIFAR-10, including the Tensorflow library. The experimental results demonstrate that the proposed scheme creates a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions (1.325 and 34.762 for MNIST and CIFAR-10, respectively).
format	article
author	Hyun Kwon Yongchul Kim Hyunsoo Yoon Daeseon Choi
author_facet	Hyun Kwon Yongchul Kim Hyunsoo Yoon Daeseon Choi
author_sort	Hyun Kwon
title	Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
title_short	Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
title_full	Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
title_fullStr	Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
title_full_unstemmed	Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes
title_sort	selective untargeted evasion attack: an adversarial example that will not be classified as certain avoided classes
publisher	IEEE
publishDate	2019
url	https://doaj.org/article/945f11f2fb4b42cb9e89bca0ee090bf1
work_keys_str_mv	AT hyunkwon selectiveuntargetedevasionattackanadversarialexamplethatwillnotbeclassifiedascertainavoidedclasses AT yongchulkim selectiveuntargetedevasionattackanadversarialexamplethatwillnotbeclassifiedascertainavoidedclasses AT hyunsooyoon selectiveuntargetedevasionattackanadversarialexamplethatwillnotbeclassifiedascertainavoidedclasses AT daeseonchoi selectiveuntargetedevasionattackanadversarialexamplethatwillnotbeclassifiedascertainavoidedclasses
_version_	1718420680303706112

Selective Untargeted Evasion Attack: An Adversarial Example That Will Not Be Classified as Certain Avoided Classes

Ejemplares similares