{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T02:47:12Z","timestamp":1773110832698,"version":"3.50.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61831015"],"award-info":[{"award-number":["61831015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61927809"],"award-info":[{"award-number":["61927809"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61901260"],"award-info":[{"award-number":["61901260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61521062"],"award-info":[{"award-number":["61521062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61527804"],"award-info":[{"award-number":["61527804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1109\/tnnls.2020.3039295","type":"journal-article","created":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T01:14:43Z","timestamp":1607562883000},"page":"1051-1065","source":"Crossref","is-referenced-by-count":28,"title":["SMGEA: A New Ensemble Adversarial Attack Powered by Long-Term Gradient Memories"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-4348","authenticated-orcid":false,"given":"Zhaohui","family":"Che","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Digital Media Processing and Transmissions, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-0335","authenticated-orcid":false,"given":"Ali","family":"Borji","sequence":"additional","affiliation":[{"name":"MarkableAI Inc, Brooklyn, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Digital Media Processing and Transmissions, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5306-9189","authenticated-orcid":false,"given":"Suiyi","family":"Ling","sequence":"additional","affiliation":[{"name":"Équipe Image, Perception et Interaction, Laboratoire des Sciences du Numérique de Nantes, Université de Nantes, Nantes, France"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Digital Media Processing and Transmissions, Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-7063","authenticated-orcid":false,"given":"Patrick","family":"Le Callet","sequence":"additional","affiliation":[{"name":"Équipe Image, Perception et Interaction, Laboratoire des Sciences du Numérique de Nantes, Université de Nantes, Nantes, France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref2","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Szegedy"},{"key":"ref3","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goodfellow"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"ref5","first-page":"1","article-title":"Delving into transferable adversarial examples and black-box attacks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2612175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496306"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978392"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00790"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.153"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref13","first-page":"1","article-title":"Generating natural adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/134"},{"key":"ref15","first-page":"2137","article-title":"Black-box adversarial attacks with limited queries and information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilyas"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301742"},{"key":"ref18","article-title":"Prior convictions: Black-box adversarial attacks with bandits and priors","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ilyas"},{"key":"ref19","first-page":"3825","article-title":"Subspace attack: Exploiting promising subspaces for query-efficient black-box attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref20","first-page":"10934","article-title":"Improving black-box adversarial attacks with a transfer-based prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.172"},{"key":"ref24","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2935967"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref27","first-page":"1","article-title":"A hierarchical model for device placement","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mirhoseini"},{"key":"ref28","volume-title":"Efficient Backprop in Neural Networks: Tricks of the Trade","author":"LeCun","year":"1998"},{"key":"ref29","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Keskar"},{"key":"ref30","first-page":"1","article-title":"Structured adversarial attack: Towards general implementation and better interpretability","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref31","first-page":"1","article-title":"Detection of deepfake video manipulation","volume-title":"Proc. 20th Irish Mach. Vis. Image Process. Conf.","author":"Koopman"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. for Learn. Representations","author":"Kingma"},{"key":"ref33","volume-title":"Online saliency prediction system Deepgaze-II","author":"Kummerer","year":"2017"},{"key":"ref34","volume-title":"Online saliency prediction system SALICON","author":"Huang","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5743"},{"key":"ref36","first-page":"1","article-title":"Ensemble adversarial training: Attacks and defenses","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tram\u00e8r"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2861800"},{"key":"ref43","first-page":"1","article-title":"Adversarial manipulation of deep representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sabour"},{"key":"ref44","article-title":"Towards a unified min-max framework for adversarial exploration and robustness","author":"Wang","year":"2019","journal-title":"arXiv:1906.03563"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref46","first-page":"1","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12 no","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"ref47","first-page":"26","article-title":"Lecture 6.5-RMSProp: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_39"},{"key":"ref49","first-page":"12905","article-title":"Cross-domain transferability of adversarial perturbations","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Naseer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00723"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref56","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref57","volume-title":"et al. Mit Saliency Benchmark","author":"Bylinskii","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref59","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref60","volume-title":"cleverhans v2. 0.0: An adversarial machine learning library","author":"Papernot","year":"2016"},{"key":"ref61","article-title":"Advertorch v0.1: An adversarial robustness toolbox based on PyTorch","author":"Weiguang Ding","year":"2019","journal-title":"arXiv:1902.07623"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref63","article-title":"CAT2000: A large scale fixation dataset for boosting saliency research","author":"Borji","year":"2015","journal-title":"arXiv:1505.03581"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40602-7_39"},{"key":"ref65","volume-title":"Online Google Satellite Dataset","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref67","volume-title":"Adversarial Attack and Defense Competition","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2936024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"ref75","article-title":"SalGAN: Visual saliency prediction with generative adversarial networks","author":"Pan","year":"2017","journal-title":"arXiv:1701.01081"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref78","article-title":"OpenSalicon: An open source implementation of the salicon saliency model","author":"Thomas","year":"2016","journal-title":"arXiv:1606.00110"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2945857"},{"key":"ref80","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref85","first-page":"1319","article-title":"Maxout networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow"},{"key":"ref86","article-title":"Adversarial attacks against deep saliency models","author":"Che","year":"2019","journal-title":"arXiv:1904.01231"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9722951\/09288740.pdf?arnumber=9288740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:34:56Z","timestamp":1704843296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9288740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":86,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3039295","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}