{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T23:12:40Z","timestamp":1773011560576,"version":"3.50.1"},"reference-count":36,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T00:00:00Z","timestamp":1623024000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFB0801900"],"award-info":[{"award-number":["2017YFB0801900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Security and Communication Networks"],"published-print":{"date-parts":[[2021,6,7]]},"abstract":"<jats:p>Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems. Sophisticated adversarial examples with strong attack performance can also be used as a tool to evaluate the robustness of a model. However, the success rate of adversarial attacks can be further improved in black-box environments. Therefore, this study combines a modified Adam gradient descent algorithm with the iterative gradient-based attack method. The proposed Adam iterative fast gradient method is then used to improve the transferability of adversarial examples. Extensive experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. By extending our method, we achieved a state-of-the-art attack success rate of 95.0% on defense models.<\/jats:p>","DOI":"10.1155\/2021\/9983309","type":"journal-article","created":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T23:31:58Z","timestamp":1623108718000},"page":"1-9","source":"Crossref","is-referenced-by-count":7,"title":["Boosting Adversarial Attacks on Neural Networks with Better Optimizer"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3927-0932","authenticated-orcid":true,"given":"Heng","family":"Yin","sequence":"first","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1649-7336","authenticated-orcid":true,"given":"Hengwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7641-9014","authenticated-orcid":true,"given":"Jindong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6231-1582","authenticated-orcid":true,"given":"Ruiyu","family":"Dou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K. Simonyan","year":"2014"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"5","article-title":"Intriguing properties of neural networks","author":"C. Szegedy"},{"key":"6","article-title":"Explaining and harnessing adversarial examples","author":"I. J. Goodfellow","year":"2014"},{"key":"7","article-title":"Adversarial examples in the physical world","author":"A. Kurakin","year":"2016"},{"key":"8","first-page":"9185","article-title":"Boosting adversarial attacks with momentum","author":"Y. Dong"},{"key":"9","first-page":"2725","article-title":"Improving transferability of adversarial examples with input diversity","author":"C. Xie"},{"key":"10","first-page":"39","article-title":"Towards evaluating the robustness of neural networks","author":"N. Carlini"},{"key":"11","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"Y. Liu","year":"2016"},{"key":"12","article-title":"Black-box adversarial attacks with limited queries and information","author":"A. I. Ilyas","year":"2018"},{"key":"13","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"D. Wierstra","year":"2014","journal-title":"Journal of Machine Learning and Research"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321749"},{"key":"15","article-title":"Decision-based adversarial attacks: reliable attacks against black-box machine learning models","author":"W. Brendel","year":"2017"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"17","article-title":"A method for stochastic optimization","author":"D. P. Kingma","year":"2014"},{"key":"18","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","author":"J. Lin"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"20","article-title":"Towards deep learning models resistant to adversarial attacks","author":"A. Madry","year":"2018"},{"key":"21","first-page":"582","article-title":"Distillation as a defense to adversarial perturbations against deep neural networks","author":"N. Papernot"},{"key":"22","article-title":"Thermometer encoding: one hot way to resist adversarial examples","author":"J. Buckman"},{"key":"23","article-title":"Countering adversarial images using input transforma-tions","author":"C. Guo","year":"2017"},{"key":"24","article-title":"Defense-gan: protecting classifiers against adversarial attacks using generative models","author":"P. Samangouei","year":"2018"},{"key":"25","article-title":"Wasserstein smoothing: Certified robustness against wasserstein adversarial attacks","author":"A. Levine"},{"key":"26","article-title":"Multitask learning strengthens adversarial robustness","author":"C. Mao","year":"2020"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9101634"},{"key":"28","article-title":"Certified adversarial robustness via randomized smoothing","author":"J. M. Cohen","year":"2019"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9111957"},{"key":"30","article-title":"Adversarial machine learning at scale","author":"A. Kurakin","year":"2016"},{"key":"31","article-title":"Ensemble adversarial training: attacks and defenses","author":"F. Tram\u00e8r","year":"2017"},{"key":"32","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"I. Sutskever"},{"key":"33","article-title":"Lecture 6.5-RMSProp, coursera: neural networks for machine learning","author":"T. Tieleman","year":"2012"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"35","doi-asserted-by":"crossref","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"C. Szegedy","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"}],"container-title":["Security and Communication Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9983309.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9983309.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9983309.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T07:14:28Z","timestamp":1672384468000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/scn\/2021\/9983309\/"}},"subtitle":[],"editor":[{"given":"Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,6,7]]},"references-count":36,"alternative-id":["9983309","9983309"],"URL":"https:\/\/doi.org\/10.1155\/2021\/9983309","relation":{},"ISSN":["1939-0122","1939-0114"],"issn-type":[{"value":"1939-0122","type":"electronic"},{"value":"1939-0114","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6,7]]}}}