{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:20:22Z","timestamp":1783056022518,"version":"3.54.6"},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2024F023"],"award-info":[{"award-number":["LH2024F023"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012335","name":"National Defense Basic Scientific Research Program of China","doi-asserted-by":"publisher","award":["JCKY2023603C043"],"award-info":[{"award-number":["JCKY2023603C043"]}],"id":[{"id":"10.13039\/501100012335","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Electrical Engineering"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.compeleceng.2026.111187","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:35:32Z","timestamp":1777368932000},"page":"111187","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Fast adversarial training based on implicit sharpness aware regularization"],"prefix":"10.1016","volume":"135","author":[{"given":"Liyao","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanghui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenbang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dechen","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compeleceng.2026.111187_b1","unstructured":"Szegedy Christian, Zaremba Wojciech, Sutskever Ilya. Intriguing properties of neural networks. In: International conference on learning representations. 2014."},{"key":"10.1016\/j.compeleceng.2026.111187_b2","unstructured":"Goodfellow Ian J, Shlens Jonathon, Szegedy Christian. Explaining and harnessing adversarial examples. In: International conference on learning representations. 2015."},{"key":"10.1016\/j.compeleceng.2026.111187_b3","doi-asserted-by":"crossref","unstructured":"Chi Lijun, Msahli Mounira, Zhang Qingjie, Qiu Han, Zhang Tianwei, Memmi Gerard, Qiu Meikang. Adversarial attacks on autonomous driving systems in the physical world: a survey. IEEE Trans Intell Veh 2024.","DOI":"10.1109\/TIV.2024.3484152"},{"key":"10.1016\/j.compeleceng.2026.111187_b4","unstructured":"Madry Aleksander, Makelov Aleksandar, Schmidt Ludwig. Towards deep learning models resistant to adversarial attacks. In: International conference on learning representations. 2018."},{"key":"10.1016\/j.compeleceng.2026.111187_b5","unstructured":"Wong Eric, Rice Leslie, Kolter J Zico. Fast is better than free: Revisiting adversarial training. In: International conference on learning representations. 2019."},{"key":"10.1016\/j.compeleceng.2026.111187_b6","article-title":"Understanding and improving fast adversarial training","volume":"33","author":"Andriushchenko","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.compeleceng.2026.111187_b7","doi-asserted-by":"crossref","unstructured":"Kim Hoki, Lee Woojin, Lee Jaewook. Understanding catastrophic overfitting in single-step adversarial training. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35. 2021, p. 8119\u201327.","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"10.1016\/j.compeleceng.2026.111187_b8","doi-asserted-by":"crossref","unstructured":"Park Geon Yeong, Lee Sang Wan. Reliably fast adversarial training via latent adversarial perturbation. In: International conference on computer vision. 2021.","DOI":"10.1109\/ICCV48922.2021.00766"},{"key":"10.1016\/j.compeleceng.2026.111187_b9","series-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"10.1016\/j.compeleceng.2026.111187_b10","unstructured":"Foret Pierre, Kleiner Ariel, Mobahi Hossein, Neyshabur Behnam. Sharpness-aware minimization for efficiently improving generalization. In: International conference on learning representations. 2021."},{"key":"10.1016\/j.compeleceng.2026.111187_b11","series-title":"Proceedings of the 35th international conference on machine learning","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume":"Vol. 80","author":"Athalye","year":"2018"},{"key":"10.1016\/j.compeleceng.2026.111187_b12","series-title":"Zerograd: Mitigating and explaining catastrophic overfitting in fgsm adversarial training","author":"Golgooni","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111187_b13","series-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"key":"10.1016\/j.compeleceng.2026.111187_b14","doi-asserted-by":"crossref","unstructured":"He Zhezhi, Rakin Adnan Siraj, Fan Deliang. Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, p. 588\u201397.","DOI":"10.1109\/CVPR.2019.00068"},{"key":"10.1016\/j.compeleceng.2026.111187_b15","unstructured":"Li Hao, Xu Zheng, Taylor Gavin, Studer Christoph, Goldstein Tom. Visualizing the loss landscape of neural nets. In: Proceedings of the 32nd international conference on neural information processing systems. 2018, p. 6391\u2013401."},{"key":"10.1016\/j.compeleceng.2026.111187_b16","unstructured":"Athalye Anish, Carlini Nicholas, Wagner David. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In: ICML. 2018."},{"key":"10.1016\/j.compeleceng.2026.111187_b17","doi-asserted-by":"crossref","unstructured":"Liu Xuanqing, Cheng Minhao, Zhang Huan, Hsieh Cho-Jui. Towards robust neural networks via random self-ensemble. In: Proceedings of the European conference on computer vision. 2018, p. 369\u201385.","DOI":"10.1007\/978-3-030-01234-2_23"},{"key":"10.1016\/j.compeleceng.2026.111187_b18","doi-asserted-by":"crossref","unstructured":"Stutz David, Hein Matthias, Schiele Bernt. Relating adversarially robust generalization to flat minima. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, p. 7807\u201317.","DOI":"10.1109\/ICCV48922.2021.00771"},{"key":"10.1016\/j.compeleceng.2026.111187_b19","series-title":"European conference on computer vision","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"He","year":"2016"},{"key":"10.1016\/j.compeleceng.2026.111187_b20","doi-asserted-by":"crossref","unstructured":"He Tong, Zhang Zhi, Zhang Hang, Zhang Zhongyue, Xie Junyuan, Li Mu. Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, p. 558\u201367.","DOI":"10.1109\/CVPR.2019.00065"},{"key":"10.1016\/j.compeleceng.2026.111187_b21","unstructured":"Croce Francesco, Hein Matthias. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: ICLR. 2020."},{"key":"10.1016\/j.compeleceng.2026.111187_b22","unstructured":"Shafahi Ali, Najibi Mahyar, Ghiasi Amin, Xu Zheng, Dickerson John, Studer Christoph, Davis Larry S, Taylor Gavin, Goldstein Tom. Adversarial training for free!. In: Proceedings of the 33rd international conference on neural information processing systems. 2019, p. 3358\u201369."},{"key":"10.1016\/j.compeleceng.2026.111187_b23","doi-asserted-by":"crossref","first-page":"4547","DOI":"10.1109\/TIFS.2024.3377004","article-title":"Fast propagation is better: Accelerating single-step adversarial training via sampling subnetworks","volume":"19","author":"Jia","year":"2024","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10.1016\/j.compeleceng.2026.111187_b24","doi-asserted-by":"crossref","first-page":"67866","DOI":"10.52202\/075280-2968","article-title":"Eliminating catastrophic overfitting via abnormal adversarial examples regularization","volume":"36","author":"Lin","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.compeleceng.2026.111187_b25","doi-asserted-by":"crossref","unstructured":"Du Jiawei, Yan Hanshu, Feng Jiashi, Zhou Joey Tianyi, Zhen Liangli, Goh Rick Siow Mong, Tan Vincent. Efficient sharpness-aware minimization for improved training of neural networks. In: International conference on learning representations. 2022.","DOI":"10.52202\/068431-1703"},{"key":"10.1016\/j.compeleceng.2026.111187_b26","series-title":"Conference on learning theory","first-page":"2315","article-title":"Shape matters: Understanding the implicit bias of the noise covariance","author":"HaoChen","year":"2021"},{"key":"10.1016\/j.compeleceng.2026.111187_b27","series-title":"International conference on machine learning","first-page":"7654","article-title":"The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects","author":"Zhu","year":"2019"},{"key":"10.1016\/j.compeleceng.2026.111187_b28","series-title":"International conference on machine learning","first-page":"10367","article-title":"On the noisy gradient descent that generalizes as sgd","author":"Wu","year":"2020"},{"key":"10.1016\/j.compeleceng.2026.111187_b29","unstructured":"Xie Zeke, Sato Issei, Sugiyama Masashi. A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima. In: International conference on learning representations. 2021."},{"issue":"1","key":"10.1016\/j.compeleceng.2026.111187_b30","first-page":"4873","article-title":"Stochastic gradient descent as approximate bayesian inference","volume":"18","author":"Mandt","year":"2017","journal-title":"J Mach Learn Res"}],"container-title":["Computers and Electrical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626002594?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0045790626002594?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:50:44Z","timestamp":1783054244000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0045790626002594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":30,"alternative-id":["S0045790626002594"],"URL":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111187","relation":{},"ISSN":["0045-7906"],"issn-type":[{"value":"0045-7906","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fast adversarial training based on implicit sharpness aware regularization","name":"articletitle","label":"Article Title"},{"value":"Computers and Electrical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compeleceng.2026.111187","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"111187"}}