{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:06:03Z","timestamp":1784822763467,"version":"3.55.0"},"reference-count":128,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3208131","type":"journal-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:29:21Z","timestamp":1663702161000},"page":"102266-102291","source":"Crossref","is-referenced-by-count":85,"title":["Adversarial Deep Learning: A Survey on Adversarial Attacks and Defense Mechanisms on Image Classification"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9339-1685","authenticated-orcid":false,"given":"Samer Y.","family":"Khamaiseh","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, Miami University, Oxford, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Bagagem","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah","family":"Al-Alaj","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Wesleyan University, Virginia Beach, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathew","family":"Mancino","sequence":"additional","affiliation":[{"name":"CACI International, Norfolk, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hakam W.","family":"Alomari","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Miami University, Oxford, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254806"},{"key":"ref2","volume-title":"How drive.AI is mastering autonomous driving with deep learning","author":"Ackerman","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC48688.2020.0-157"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2019.2959268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-56769-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MESA.2018.8449150"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2019.00621"},{"key":"ref12","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3487890"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3127960"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950779"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref24","volume-title":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep Learning","author":"Heaton","year":"2018"},{"key":"ref25","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref28","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11302"},{"key":"ref31","article-title":"Adversarial attacks and defences: A survey","author":"Chakraborty","year":"2018","journal-title":"arXiv:1810.00069"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10761.001.0001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/0471497398.mm421"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7439(97)00061-0"},{"key":"ref35","volume-title":"Sigmoid Function","year":"2020"},{"key":"ref36","volume-title":"Softmax Function","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.33564\/ijeast.2020.v04i12.054"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3345660"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/NFV-SDN50289.2020.9289908"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3270101.3270106"},{"key":"ref43","article-title":"Query-efficient black-box adversarial examples (superceded)","author":"Ilyas","year":"2017","journal-title":"arXiv:1712.07113"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1654988.1654990"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207272"},{"key":"ref46","first-page":"97","article-title":"Support vector machines under adversarial label noise","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Biggio"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SSP.2016.7551832"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00137"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2977378"},{"key":"ref50","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00045"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/9781118723203"},{"key":"ref55","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref57","volume-title":"Adversarial Examples in the Physical World","author":"Kurakin","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref59","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Croce"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3134600.3134635"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/a13110268"},{"key":"ref63","article-title":"Accurate, reliable and fast robustness evaluation","author":"Brendel","year":"2019","journal-title":"arXiv:1907.01003"},{"key":"ref64","first-page":"6808","article-title":"Wasserstein adversarial examples via projected Sinkhorn iterations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Wong"},{"issue":"7","key":"ref65","first-page":"52","article-title":"On a space of totally additive functions","volume":"13","author":"Kantorovich","year":"1958","journal-title":"Vestnik St. Petersburg Univ., Math."},{"key":"ref66","article-title":"Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates","author":"Ghiasi","year":"2020","journal-title":"arXiv:2003.08937"},{"key":"ref67","article-title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models","author":"Brendel","year":"2017","journal-title":"arXiv:1712.04248"},{"key":"ref68","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref69","first-page":"1802","article-title":"Exploring the landscape of spatial robustness","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Engstrom"},{"key":"ref70","article-title":"UPSET and ANGRI: Breaking high performance image classifiers","author":"Sarkar","year":"2017","journal-title":"arXiv:1707.01159"},{"key":"ref71","article-title":"Houdini: Fooling deep structured prediction models","author":"Cisse","year":"2017","journal-title":"arXiv:1707.05373"},{"key":"ref72","first-page":"2484","article-title":"Simple black-box adversarial attacks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2010.2059031"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00930"},{"key":"ref75","article-title":"Robustness assessment for adversarial machine learning: Problems, solutions and a survey of current neural networks and defenses","author":"Vargas","year":"2019","journal-title":"arXiv:1906.06026"},{"key":"ref76","article-title":"The CMA evolution strategy: A tutorial","author":"Hansen","year":"2016","journal-title":"arXiv:1604.00772"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00123"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107256"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00348"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref81","article-title":"Poisoning attacks against support vector machines","author":"Biggio","year":"2012","journal-title":"arXiv:1206.6389"},{"key":"ref82","article-title":"Detecting backdoor attacks on deep neural networks by activation clustering","author":"Chen","year":"2018","journal-title":"arXiv:1811.03728"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP48549.2020.00019"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417253"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref86","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","author":"Shafahi","year":"2018","journal-title":"arXiv:1804.00792"},{"key":"ref87","first-page":"7614","article-title":"Transferable clean-label poisoning attacks on deep neural nets","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP51992.2021.00021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489592"},{"key":"ref90","first-page":"1345","article-title":"High accuracy and high fidelity extraction of neural networks","volume-title":"Proc. 29th USENIX Secur. Symp. (USENIX Secur.)","author":"Jagielski"},{"key":"ref91","first-page":"17","article-title":"Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing","volume-title":"Proc. 23rd USENIX Secur. Symp. (USENIX Secur.)","author":"Fredrikson"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref93","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref95","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Qin"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref97","article-title":"Joint 2D-3D-semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv:1702.01105"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00935"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.084"},{"key":"ref101","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329073"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11504"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref107","article-title":"DeepCloak: Masking deep neural network models for robustness against adversarial samples","author":"Gao","year":"2017","journal-title":"arXiv:1702.06763"},{"key":"ref108","first-page":"854","article-title":"Parseval networks: Improving robustness to adversarial examples","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Cisse"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.56"},{"key":"ref110","article-title":"On detecting adversarial perturbations","author":"Hendrik Metzen","year":"2017","journal-title":"arXiv:1702.04267"},{"key":"ref111","article-title":"Towards deep neural network architectures robust to adversarial examples","author":"Gu","year":"2014","journal-title":"arXiv:1412.5068"},{"key":"ref112","article-title":"Adversarial training methods for semi-supervised text classification","author":"Miyato","year":"2016","journal-title":"arXiv:1605.07725"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.485"},{"key":"ref114","article-title":"A study of the effect of JPG compression on adversarial images","author":"Karolina Dziugaite","year":"2016","journal-title":"arXiv:1608.00853"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362326"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417231"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00357"},{"key":"ref118","article-title":"Feature squeezing: Detecting adversarial examples in deep neural networks","author":"Xu","year":"2017","journal-title":"arXiv:1704.01155"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"ref120","first-page":"281","article-title":"Classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probab.","author":"MacQueen"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2509509"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref123","article-title":"Spectral signatures in backdoor attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Tran"},{"key":"ref124","article-title":"Adversarial vulnerability for any classifier","author":"Fawzi","year":"2018","journal-title":"arXiv:1802.08686"},{"key":"ref125","article-title":"Attacking adversarial attacks as a defense","author":"Wu","year":"2021","journal-title":"arXiv:2106.04938"},{"key":"ref126","article-title":"Provably minimally-distorted adversarial examples","author":"Carlini","year":"2017","journal-title":"arXiv:1709.10207"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5663-3"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09895425.pdf?arnumber=9895425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:47:54Z","timestamp":1705960074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9895425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":128,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3208131","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}