Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example

Deep neural networks (DNNs) show superior performance in image and speech recognition. However, adversarial examples created by adding a little noise to an original sample can lead to misclassification by a DNN. Conventional studies on adversarial examples have focused on ways of causing misclassifi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyun Kwon, Hyunsoo Yoon, Daeseon Choi
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2019
Materias:	Deep neural network (DNN) adversarial example machine learning evasion attack restricted area Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/18e15e9596274820aa6894a854aac8f4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:18e15e9596274820aa6894a854aac8f4
record_format	dspace
spelling	oai:doaj.org-article:18e15e9596274820aa6894a854aac8f42021-11-19T00:02:46ZRestricted Evasion Attack: Generation of Restricted-Area Adversarial Example2169-353610.1109/ACCESS.2019.2915971https://doaj.org/article/18e15e9596274820aa6894a854aac8f42019-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/8710245/https://doaj.org/toc/2169-3536Deep neural networks (DNNs) show superior performance in image and speech recognition. However, adversarial examples created by adding a little noise to an original sample can lead to misclassification by a DNN. Conventional studies on adversarial examples have focused on ways of causing misclassification by a DNN by modulating the entire image. However, in some cases, a restricted adversarial example may be required in which only certain parts of the image are modified rather than the entire image and that results in misclassification by the DNN. For example, when the placement of a road sign has already been completed, an attack may be required that will change only a specific part of the sign, such as by placing a sticker on it, to cause misidentification of the entire image. As another example, an attack may be required that causes a DNN to misinterpret images according to a minimal modulation of the outside border of the image. In this paper, we propose a new restricted adversarial example that modifies only a restricted area to cause misclassification by a DNN while minimizing distortion from the original sample. It can also select the size of the restricted area. We used the CIFAR10 and ImageNet datasets to evaluate the performance. We measured the attack success rate and distortion of the restricted adversarial example while adjusting the size, shape, and position of the restricted area. The results show that the proposed scheme generates restricted adversarial examples with a 100% attack success rate in a restricted area of the whole image (approximately 14% for CIFAR10 and 1.07% for ImageNet) while minimizing the distortion distance.Hyun KwonHyunsoo YoonDaeseon ChoiIEEEarticleDeep neural network (DNN)adversarial examplemachine learningevasion attackrestricted areaElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 7, Pp 60908-60919 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep neural network (DNN) adversarial example machine learning evasion attack restricted area Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep neural network (DNN) adversarial example machine learning evasion attack restricted area Electrical engineering. Electronics. Nuclear engineering TK1-9971 Hyun Kwon Hyunsoo Yoon Daeseon Choi Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
description	Deep neural networks (DNNs) show superior performance in image and speech recognition. However, adversarial examples created by adding a little noise to an original sample can lead to misclassification by a DNN. Conventional studies on adversarial examples have focused on ways of causing misclassification by a DNN by modulating the entire image. However, in some cases, a restricted adversarial example may be required in which only certain parts of the image are modified rather than the entire image and that results in misclassification by the DNN. For example, when the placement of a road sign has already been completed, an attack may be required that will change only a specific part of the sign, such as by placing a sticker on it, to cause misidentification of the entire image. As another example, an attack may be required that causes a DNN to misinterpret images according to a minimal modulation of the outside border of the image. In this paper, we propose a new restricted adversarial example that modifies only a restricted area to cause misclassification by a DNN while minimizing distortion from the original sample. It can also select the size of the restricted area. We used the CIFAR10 and ImageNet datasets to evaluate the performance. We measured the attack success rate and distortion of the restricted adversarial example while adjusting the size, shape, and position of the restricted area. The results show that the proposed scheme generates restricted adversarial examples with a 100% attack success rate in a restricted area of the whole image (approximately 14% for CIFAR10 and 1.07% for ImageNet) while minimizing the distortion distance.
format	article
author	Hyun Kwon Hyunsoo Yoon Daeseon Choi
author_facet	Hyun Kwon Hyunsoo Yoon Daeseon Choi
author_sort	Hyun Kwon
title	Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
title_short	Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
title_full	Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
title_fullStr	Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
title_full_unstemmed	Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example
title_sort	restricted evasion attack: generation of restricted-area adversarial example
publisher	IEEE
publishDate	2019
url	https://doaj.org/article/18e15e9596274820aa6894a854aac8f4
work_keys_str_mv	AT hyunkwon restrictedevasionattackgenerationofrestrictedareaadversarialexample AT hyunsooyoon restrictedevasionattackgenerationofrestrictedareaadversarialexample AT daeseonchoi restrictedevasionattackgenerationofrestrictedareaadversarialexample
_version_	1718420653104693248

Restricted Evasion Attack: Generation of Restricted-Area Adversarial Example

Ejemplares similares