{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:07:59Z","timestamp":1783930079626,"version":"3.55.0"},"reference-count":41,"publisher":"Institution of Engineering and Technology (IET)","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576214"],"award-info":[{"award-number":["62576214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376161"],"award-info":[{"award-number":["62376161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176160"],"award-info":[{"award-number":["62176160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024B1515020109"],"award-info":[{"award-number":["2024B1515020109"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Adversarial training (AT) is widely regarded as a crucial defense method for deep neural networks against adversarial attacks. Most of the existing AT methods suffer from the problems of insufficient coverage of perturbation space and robust overfitting. In view of this, we propose an AT framework with adaptive example reuse (AT\u2010AER) to help improve the adversarial robustness of deep models. In AT\u2010AER, a new concept named 2nd\u2010order adversarial example (AE) is proposed by adaptively filtering AEs generated during the historical training phase, which achieves sufficient coverage of diverse attack directions. Meanwhile, by analysing the fundamental causes of robust overfitting, we propose the strategies of wave descending learning rate (WDLR), cosine increasing weight decay (CIWD) and cosine increasing attack strength (CIAS) in collaboration with AT\u2010AER to optimise models. In addition, the Stochastic Weight Averaging (SWA) technique is introduced to further improve the stability of training. Finally, experiments on three benchmark datasets show that AT\u2010AER exhibits significant advantages in the face of strong adversarial attacks. Its adaptive mechanism effectively alleviates the phenomenon of robust overfitting where the performance difference between the best model and the last model is less than 1%. The study further reveals that using traditional weak attacks (e.g.,\u00a0FGSM) to evaluate the robustness of models may lead to a false sense of reliability, indicating the necessity of using strong attacks for robustness evaluation. This study provides a solution for AT that balances efficiency and performance.<\/jats:p>","DOI":"10.1049\/cit2.70121","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:20:08Z","timestamp":1773854408000},"page":"769-783","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AT\u2010AER: Adversarial Training With Adaptive Example Reuse"],"prefix":"10.1049","volume":"11","author":[{"given":"Meng","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence Shenzhen University  Shenzhen China"},{"name":"National Engineering Laboratory for Big Data System Computing Technology Shenzhen University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanting","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Dongguan University of Technology  Dongguan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2586-5604","authenticated-orcid":false,"given":"Ran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Shenzhen University  Shenzhen China"},{"name":"National Engineering Laboratory for Big Data System Computing Technology Shenzhen University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-4728","authenticated-orcid":false,"given":"Xizhao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering Shenzhen University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rihao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences Shenzhen University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering Shenzhen University  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12356"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12406"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12403"},{"key":"e_1_2_11_5_1","volume-title":"Proceedings of the 2nd International Conference on Learning Representations (ICLR)","author":"Szegedy C.","year":"2014"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12028"},{"key":"e_1_2_11_7_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR)","author":"Goodfellow I.","year":"2015"},{"key":"e_1_2_11_8_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR)","author":"Madry A.","year":"2018"},{"key":"e_1_2_11_9_1","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)","author":"Kurakina A.","year":"2017"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"e_1_2_11_11_1","first-page":"7472","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Zhang H.","year":"2019"},{"key":"e_1_2_11_12_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR)","author":"Wang Y.","year":"2020"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110394"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.12.041"},{"issue":"20","key":"e_1_2_11_15_1","first-page":"1","article-title":"Regularizing Hard Examples Improves Adversarial Robustness","volume":"26","author":"Lee H.","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.02263"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/23m1564560"},{"key":"e_1_2_11_18_1","first-page":"5652","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR)","author":"Wang H.","year":"2022"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24123909"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3381180"},{"key":"e_1_2_11_21_1","first-page":"24776","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li Z.","year":"2018"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","unstructured":"L.Zhao W. W.Ng J.Zhang andH.Zhou \u201cMitigating Robust Overfitting and Semantic Distortion via Dual\u2010Decoupled Adversarial Robustness Distillation \u201d (2025) https:\/\/ssrn.com\/abstract=5475990.","DOI":"10.2139\/ssrn.5475990"},{"key":"e_1_2_11_23_1","first-page":"7377","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems (NIPS)","author":"Zhang J.","year":"2020"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_18"},{"key":"e_1_2_11_25_1","first-page":"13388","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jia X.","year":"2022"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3371211"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_9"},{"key":"e_1_2_11_28_1","first-page":"876","volume-title":"Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Izmailov P.","year":"2018"},{"key":"e_1_2_11_29_1","unstructured":"A.Krizhevsky \u201cLearning Multiple Layers of Features From Tiny Images \u201d (Master\u2019s thesis University of Toronto 2009)."},{"key":"e_1_2_11_30_1","volume-title":"Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning","author":"Netzer Y.","year":"2011"},{"key":"e_1_2_11_31_1","first-page":"2958","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems (NIPS)","author":"Wu D.","year":"2020"},{"key":"e_1_2_11_32_1","first-page":"25595","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML)","author":"Yu C.","year":"2022"},{"key":"e_1_2_11_33_1","first-page":"74461","volume-title":"Proceedings of the 38th Conference on Neural Information Processing Systems (NIPS)","author":"Cui J.","year":"2024"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01468"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2019.2890858"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"e_1_2_11_37_1","first-page":"2206","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Groce F.","year":"2020"},{"key":"e_1_2_11_38_1","first-page":"2196","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Groce F.","year":"2020"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"e_1_2_11_41_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR)","author":"Wong E.","year":"2020"},{"key":"e_1_2_11_42_1","first-page":"567","volume-title":"Proceedings of the 17th European Conference on Computer Vision (ECCV)","author":"Jia X.","year":"2022"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70121","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70121","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:25:04Z","timestamp":1783927504000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1049\/cit2.70121"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70121","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"2025-11-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}