Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey

Deep Learning is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that deep le...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Naveed Akhtar, Ajmal Mian, Navid Kardan, Mubarak Shah
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Adversarial examples adversarial defense adversarial machine learning black-box attack deep learning perturbation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/e42f524a20ca4b5192c3b0da7c72e541
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e42f524a20ca4b5192c3b0da7c72e541
record_format	dspace
spelling	oai:doaj.org-article:e42f524a20ca4b5192c3b0da7c72e5412021-11-26T00:01:51ZAdvances in Adversarial Attacks and Defenses in Computer Vision: A Survey2169-353610.1109/ACCESS.2021.3127960https://doaj.org/article/e42f524a20ca4b5192c3b0da7c72e5412021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9614158/https://doaj.org/toc/2169-3536Deep Learning is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that deep learning is vulnerable to adversarial attacks that can manipulate its predictions by introducing visually imperceptible perturbations in images and videos. Since the discovery of this phenomenon in 2013, it has attracted significant attention of researchers from multiple sub-fields of machine intelligence. In 2018, we published the first-ever review of the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses). Many of those contributions have inspired new directions in this area, which has matured significantly since witnessing the first generation methods. Hence, as a legacy sequel of our first literature survey, this review article focuses on the advances in this area since 2018. We thoroughly discuss the first generation attacks and comprehensively cover the modern attacks and their defenses appearing in the prestigious sources of computer vision and machine learning research. Besides offering the most comprehensive literature review of adversarial attacks and defenses to date, the article also provides concise definitions of technical terminologies for the non-experts. Finally, it discusses challenges and future outlook of this direction based on the literature since the advent of this research direction.Naveed AkhtarAjmal MianNavid KardanMubarak ShahIEEEarticleAdversarial examplesadversarial defenseadversarial machine learningblack-box attackdeep learningperturbationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 155161-155196 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Adversarial examples adversarial defense adversarial machine learning black-box attack deep learning perturbation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Adversarial examples adversarial defense adversarial machine learning black-box attack deep learning perturbation Electrical engineering. Electronics. Nuclear engineering TK1-9971 Naveed Akhtar Ajmal Mian Navid Kardan Mubarak Shah Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
description	Deep Learning is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that deep learning is vulnerable to adversarial attacks that can manipulate its predictions by introducing visually imperceptible perturbations in images and videos. Since the discovery of this phenomenon in 2013, it has attracted significant attention of researchers from multiple sub-fields of machine intelligence. In 2018, we published the first-ever review of the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses). Many of those contributions have inspired new directions in this area, which has matured significantly since witnessing the first generation methods. Hence, as a legacy sequel of our first literature survey, this review article focuses on the advances in this area since 2018. We thoroughly discuss the first generation attacks and comprehensively cover the modern attacks and their defenses appearing in the prestigious sources of computer vision and machine learning research. Besides offering the most comprehensive literature review of adversarial attacks and defenses to date, the article also provides concise definitions of technical terminologies for the non-experts. Finally, it discusses challenges and future outlook of this direction based on the literature since the advent of this research direction.
format	article
author	Naveed Akhtar Ajmal Mian Navid Kardan Mubarak Shah
author_facet	Naveed Akhtar Ajmal Mian Navid Kardan Mubarak Shah
author_sort	Naveed Akhtar
title	Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
title_short	Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
title_full	Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
title_fullStr	Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
title_full_unstemmed	Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey
title_sort	advances in adversarial attacks and defenses in computer vision: a survey
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/e42f524a20ca4b5192c3b0da7c72e541
work_keys_str_mv	AT naveedakhtar advancesinadversarialattacksanddefensesincomputervisionasurvey AT ajmalmian advancesinadversarialattacksanddefensesincomputervisionasurvey AT navidkardan advancesinadversarialattacksanddefensesincomputervisionasurvey AT mubarakshah advancesinadversarialattacksanddefensesincomputervisionasurvey
_version_	1718410000480600064

Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey

Ejemplares similares