{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:35:28Z","timestamp":1773243328138,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10044-026-01629-8","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:59:42Z","timestamp":1773172782000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing fast adversarial training: precision-aware initialization with historical perturbation guidance"],"prefix":"10.1007","volume":"29","author":[{"given":"Anjum","family":"Iqbal","sequence":"first","affiliation":[]},{"given":"Weiqiang","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Yasir","family":"Iqbal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"1629_CR1","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.patrec.2023.03.001","volume":"168","author":"C Ying","year":"2023","unstructured":"Ying C, Qiaoben Y, Zhou X, Su H, Ding W, Ai J (2023) Consistent attack: universal adversarial perturbation on embodied vision navigation. Pattern Recognit Lett 168:57\u201363. https:\/\/doi.org\/10.1016\/j.patrec.2023.03.001","journal-title":"Pattern Recognit Lett"},{"issue":"2","key":"1629_CR2","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1109\/TPAMI.2022.3165024","volume":"45","author":"B Chen","year":"2023","unstructured":"Chen B et al (2023) Adversarial examples generation for deep product quantization networks on image retrieval. IEEE Trans Pattern Anal Mach Intell 45(2):1388\u20131404. https:\/\/doi.org\/10.1109\/TPAMI.2022.3165024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"1629_CR3","doi-asserted-by":"publisher","first-page":"8287","DOI":"10.1007\/s00371-023-03237-7","volume":"40","author":"KA Tychola","year":"2024","unstructured":"Tychola KA, Vrochidou E, Papakostas GA (2024) Deep learning based computer vision under the prism of 3D point clouds: a systematic review. Vis Comput 40(11):8287\u20138329. https:\/\/doi.org\/10.1007\/s00371-023-03237-7","journal-title":"Vis Comput"},{"issue":"6","key":"1629_CR4","doi-asserted-by":"publisher","first-page":"7668","DOI":"10.1109\/tpami.2022.3220849","volume":"45","author":"Q Xu","year":"2023","unstructured":"Xu Q, Yang Z, Zhao Y, Cao X, Huang Q (2023) Rethinking label flipping attack: from sample masking to sample thresholding. IEEE Trans Pattern Anal Mach Intell 45(6):7668\u20137685. https:\/\/doi.org\/10.1109\/tpami.2022.3220849","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1629_CR5","doi-asserted-by":"publisher","first-page":"2565","DOI":"10.1109\/TIFS.2023.3336527","volume":"19","author":"L Huang","year":"2024","unstructured":"Huang L, Huang Q, Qiu P, Wei S, Gao C (2024) FASTEN: fast ensemble learning for improved adversarial robustness. IEEE Trans Inf Forensics Secur 19:2565\u20132580. https:\/\/doi.org\/10.1109\/TIFS.2023.3336527","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"10","key":"1629_CR6","doi-asserted-by":"publisher","first-page":"7427","DOI":"10.1007\/s00371-024-03265-x","volume":"40","author":"Y Gan","year":"2024","unstructured":"Gan Y, Xiao X, Xiang T (2024) Attribute-guided face adversarial example generation. Vis Comput 40(10):7427\u20137437. https:\/\/doi.org\/10.1007\/s00371-024-03265-x","journal-title":"Vis Comput"},{"key":"1629_CR7","doi-asserted-by":"publisher","first-page":"5207","DOI":"10.1109\/TIFS.2024.3390609","volume":"19","author":"R Liu","year":"2024","unstructured":"Liu R, Zhou W, Zhang T, Chen K, Zhao J, Lam KY (2024) Boosting black-box attack to deep neural networks with conditional diffusion models. IEEE Trans Inf Forensics Secur 19:5207\u20135219. https:\/\/doi.org\/10.1109\/TIFS.2024.3390609","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"1629_CR8","unstructured":"C Xie, J Wang, Z Zhang, Z Ren, and A Yuille, \"Mitigating adversarial effects through randomization,\" presented at the International conference on learning representations, 2018."},{"key":"1629_CR9","doi-asserted-by":"crossref","unstructured":"W Xu, D Evans, and Y Qi, \"Feature squeezing: detecting adversarial examples in deep neural networks,\" in 25th annual network and distributed system security symposium, {NDSS}, San Diego, California, USA: the internet society, February 18\u201321 2018","DOI":"10.14722\/ndss.2018.23198"},{"key":"1629_CR10","doi-asserted-by":"publisher","unstructured":"N Papernot, PD McDaniel, X Wu, S Jha, and A Swami, \"Distillation as a defense to adversarial perturbations against deep neural networks,\" in IEEE symposium on security and privacy, {SP} {IEEE} Computer Society, pp. 582\u2013597, 2016 https:\/\/doi.org\/10.1109\/SP.2016.41","DOI":"10.1109\/SP.2016.41"},{"key":"1629_CR11","unstructured":"A Madry, A Makelov, L Schmidt, D Tsipras, and A Vladu, \"Towards deep learning models resistant to adversarial attacks,\" in 6th International conference on learning representations, ICLR, Vancouver, BC, Canada: OpenReview.net, 2018"},{"key":"1629_CR12","unstructured":"E Wong, L Rice, and JZ Kolter, \"Fast is better than free: revisiting adversarial training,\" presented at the 8th international conference on learning representations, ICLR, Addis Ababa, Ethiopia, 2020"},{"key":"1629_CR13","doi-asserted-by":"publisher","unstructured":"X Jia, Y Zhang, B Wu, K Ma, J Wang, and X Cao, \"LAS-AT: adversarial training with learnable attack strategy,\" in 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), New Orleans, LA, USA, pp. 13388\u201313398, 2022 https:\/\/doi.org\/10.1109\/CVPR52688.2022.01304","DOI":"10.1109\/CVPR52688.2022.01304"},{"key":"1629_CR14","unstructured":"IJ Goodfellow, J Shlens, and C Szegedy, \"Explaining and harnessing adversarial examples,\" presented at the 3rd international conference on learning representations, ICLR, San Diego, CA, USA, 2015"},{"key":"1629_CR15","doi-asserted-by":"publisher","first-page":"3659","DOI":"10.1109\/TIFS.2024.3359820","volume":"19","author":"H Kuang","year":"2024","unstructured":"Kuang H, Liu H, Lin X, Ji R (2024) Defense against adversarial attacks using topology aligning adversarial training. IEEE Trans Inf Forensics Secur 19:3659\u20133673. https:\/\/doi.org\/10.1109\/TIFS.2024.3359820","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"1629_CR16","unstructured":"F Tram\u00e8r, A Kurakin, N Papernot, D Boneh, and P Mcdaniel, \"Ensemble adversarial training: attacks and defenses,\" 2018. [Online]. Available: https:\/\/openreview.net\/forum?id=rkZvSe-RZ"},{"key":"1629_CR17","unstructured":"M Andriushchenko and N Flammarion, \"Understanding and improving fast adversarial training,\" presented at the Proceedings of the 34th international conference on neural information processing systems, Vancouver, BC, Canada, 2020"},{"key":"1629_CR18","doi-asserted-by":"publisher","unstructured":"Z Wang, H Wang, C Tian, and Y Jin, \"Preventing catastrophic overfitting in fast adversarial training: a bi-level optimization perspective,\" presented at the computer vision \u2013 ECCV 2024: 18th European conference, Milan, Italy, September 29\u2013October 4, 2024, Proceedings, Part XXVIII, Milan, Italy, 2024. [Online]. Available: https:\/\/doi.org\/10.1007\/978-3-031-73390-1_9.","DOI":"10.1007\/978-3-031-73390-1_9"},{"key":"1629_CR19","doi-asserted-by":"crossref","unstructured":"H Kim, W Lee, and J Lee, \"Understanding catastrophic overfitting in single-step adversarial training,\" presented at the Conference on artificial intelligence, AAAI, 2021","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"1629_CR20","unstructured":"G Sriramanan, S Addepalli, A Baburaj, and RV Babu, \"Guided adversarial attack for evaluating and enhancing adversarial defenses,\" presented at the 34th International conference on neural information processing systems, Vancouver, BC, Canada, 2020"},{"key":"1629_CR21","unstructured":"C Szegedy et al. \"Intriguing properties of neural networks,\" presented at the 2nd International conference on learning representations, {ICLR} Banff, AB, Canada, 2014"},{"key":"1629_CR22","unstructured":"C Sun et al. \"Towards lightweight black-box attacks against deep neural networks,\" presented at the International conference on neural information processing systems, New Orleans, LA, USA, 2022"},{"issue":"7","key":"1629_CR23","doi-asserted-by":"publisher","first-page":"8726","DOI":"10.1109\/TNNLS.2022.3216981","volume":"35","author":"L Lyu","year":"2024","unstructured":"Lyu L et al (2024) Privacy and robustness in federated learning: attacks and defenses. IEEE Trans Neural Netw Learning Syst 35(7):8726\u20138746. https:\/\/doi.org\/10.1109\/TNNLS.2022.3216981","journal-title":"IEEE Trans Neural Netw Learning Syst"},{"issue":"3","key":"1629_CR24","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/TPAMI.2019.2936378","volume":"43","author":"S Tang","year":"2021","unstructured":"Tang S, Huang X, Chen M, Sun C, Yang J (2021) Adversarial attack type I: cheat classifiers by significant changes. IEEE Trans Pattern Anal Mach Intell 43(3):1100\u20131109. https:\/\/doi.org\/10.1109\/TPAMI.2019.2936378","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1629_CR25","doi-asserted-by":"publisher","first-page":"2711","DOI":"10.1109\/TPAMI.2022.3176760","volume":"45","author":"X Wei","year":"2023","unstructured":"Wei X, Guo Y, Yu J (2023) Adversarial sticker: a stealthy attack method in the physical world. IEEE Trans Pattern Anal Mach Intell 45(3):2711\u20132725. https:\/\/doi.org\/10.1109\/TPAMI.2022.3176760","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1629_CR26","doi-asserted-by":"crossref","unstructured":"N Carlini and DA Wagner, \"Towards evaluating the robustness of neural networks,\" presented at the 2017 IEEE symposium on security and privacy (SP), San Jose, CA, USA, 2017.","DOI":"10.1109\/SP.2017.49"},{"key":"1629_CR27","first-page":"484","volume-title":"Computer vision\u2014ECCV","author":"M Andriushchenko","year":"2020","unstructured":"Andriushchenko M, Croce F, Flammarion N, Hein M (2020) Square attack: a query-efficient black-box adversarial attack via random search. Computer vision\u2014ECCV. Springer, Cham, pp 484\u2013501"},{"key":"1629_CR28","unstructured":"F Croce and M Hein, \"Minimally distorted adversarial examples with a fast adaptive boundary attack,\" presented at the Proceedings of the 37th international conference on machine learning, 2020"},{"issue":"12","key":"1629_CR29","doi-asserted-by":"publisher","first-page":"9536","DOI":"10.1109\/TPAMI.2021.3126733","volume":"44","author":"Y Dong","year":"2022","unstructured":"Dong Y, Cheng S, Pang T, Su H, Zhu J (2022) Query-efficient black-box adversarial attacks guided by a transfer-based prior. IEEE Trans Pattern Anal Mach Intell 44(12):9536\u20139548. https:\/\/doi.org\/10.1109\/TPAMI.2021.3126733","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1629_CR30","unstructured":"H Zhang, Y Yu, J Jiao, EP Xing, LE Ghaoui, and MI Jordan, \"Theoretically principled trade-off between robustness and accuracy,\" presented at the 36th international conference on machine learning ICML long beach, California, USA, 2019"},{"key":"1629_CR31","unstructured":"K Roth, Y Kilcher, and T Hofmann, \"Adversarial training is a form of data-dependent operator norm regularization,\" presented at the Proceedings of the 34th international conference on neural information processing systems, Vancouver, BC, Canada, 2020"},{"issue":"3","key":"1629_CR32","doi-asserted-by":"publisher","first-page":"5070","DOI":"10.1109\/TNNLS.2024.3371008","volume":"36","author":"H Huang","year":"2025","unstructured":"Huang H, Zeng Z (2025) An accelerated approach on adaptive gradient neural network for solving time-dependent linear equations: a state-triggered perspective. IEEE Trans Neural Netw Learn Syst 36(3):5070\u20135081. https:\/\/doi.org\/10.1109\/TNNLS.2024.3371008","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1629_CR33","unstructured":"G Sriramanan, S Addepalli, A Baburaj, and RV Babu, \"Towards efficient and effective adversarial training,\" presented at the Proceedings of the 35th international conference on neural information processing systems, 2021"},{"key":"1629_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2023.200258","volume":"19","author":"Z Golgooni","year":"2023","unstructured":"Golgooni Z, Saberi M, Eskandar M, Rohban MH (2023) Zerograd: costless conscious remedies for catastrophic overfitting in the FGSM adversarial training. Intell Syst Appl 19:200258. https:\/\/doi.org\/10.1016\/j.iswa.2023.200258","journal-title":"Intell Syst Appl"},{"issue":"9","key":"1629_CR35","doi-asserted-by":"publisher","first-page":"6367","DOI":"10.1109\/TPAMI.2024.3381180","volume":"46","author":"X Jia","year":"2024","unstructured":"Jia X et al (2024) Improving fast adversarial training with prior-guided knowledge. IEEE Trans Pattern Anal Mach Intell 46(9):6367\u20136383. https:\/\/doi.org\/10.1109\/TPAMI.2024.3381180","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1629_CR36","doi-asserted-by":"crossref","unstructured":"X Jia, et al., \"Prior-guided adversarial initialization for\u00a0fast adversarial training,\" in Computer vision\u2014ECCV 2022, 17th European conference, Tel Aviv, Israel: Springer, pp. 567\u2013584, 2022","DOI":"10.1007\/978-3-031-19772-7_33"},{"key":"1629_CR37","doi-asserted-by":"publisher","unstructured":"M Zhao, L Zhang, Y Kong, and B Yin, \"Fast adversarial training with smooth convergence,\" in 2023 IEEE\/CVF international conference on computer vision (ICCV), pp. 4697\u20134706, 2023. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00435","DOI":"10.1109\/ICCV51070.2023.00435"},{"key":"1629_CR38","doi-asserted-by":"publisher","first-page":"20679","DOI":"10.1109\/TASE.2025.3604283","volume":"22","author":"J Zhu","year":"2025","unstructured":"Zhu J et al (2025) Semi-supervised privacy-preserving EEG-based motor imagery classification via self and adversarial training. IEEE Trans Autom Sci Eng 22:20679\u201320690. https:\/\/doi.org\/10.1109\/TASE.2025.3604283","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"6","key":"1629_CR39","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1109\/TSMC.2024.3374068","volume":"54","author":"J Zhu","year":"2024","unstructured":"Zhu J et al (2024) Clustering environment aware learning for active domain adaptation. IEEE Trans Syst Man Cybern Syst 54(6):3891\u20133904. https:\/\/doi.org\/10.1109\/TSMC.2024.3374068","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"1629_CR40","unstructured":"A Krizhevsky, \"Learning multiple layers of features from tiny images,\" University of Toronto, 05\/08 2012"},{"key":"1629_CR41","doi-asserted-by":"publisher","unstructured":"J Deng, W Dong, R Socher, LJ Li, L Kai, and FF Li, \"ImageNet: a large-scale hierarchical image database,\" in 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255, 2009. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1629_CR42","doi-asserted-by":"publisher","unstructured":"K He, X Zhang, S Ren, and J Sun, \"Deep residual learning for image recognition,\" in 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 770\u2013778, 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1629_CR43","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer vision\u2014ECCV 2016","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. Computer vision\u2014ECCV 2016. Springer, pp 630\u2013645"},{"key":"1629_CR44","unstructured":"S Zagoruyko and N Komodakis, 2016 \"Wide residual networks,\" ArXiv, vol. abs\/1605.07146"},{"key":"1629_CR45","unstructured":"F. Croce and M. Hein, \"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,\" presented at the 37th international conference on machine learning, ICML, 2020. [Online]. Available: http:\/\/proceedings.mlr.press\/v119\/croce20b.html"},{"key":"1629_CR46","unstructured":"A Shafahi, et al. 2019 \"Adversarial training for free!,\" in 33rd international conference on neural information processing systems, NeurIPS 2019: Curran Associates Inc., pp. 3353\u20133364"},{"key":"1629_CR47","doi-asserted-by":"publisher","first-page":"4547","DOI":"10.1109\/TIFS.2024.3377004","volume":"19","author":"X Jia","year":"2024","unstructured":"Jia X, Li J, Gu J, Bai Y, Cao X (2024) Fast propagation is better: accelerating single-step adversarial training via sampling subnetworks. IEEE Trans Inf Forensics Secur 19:4547\u20134559. https:\/\/doi.org\/10.1109\/TIFS.2024.3377004","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"1629_CR48","doi-asserted-by":"publisher","first-page":"4417","DOI":"10.1109\/TIP.2022.3184255","volume":"31","author":"X Jia","year":"2022","unstructured":"Jia X, Zhang Y, Wu B, Wang J, Cao X (2022) Boosting fast adversarial training with learnable adversarial initialization. IEEE Trans Image Process 31:4417\u20134430. https:\/\/doi.org\/10.1109\/TIP.2022.3184255","journal-title":"IEEE Trans Image Process"},{"key":"1629_CR49","doi-asserted-by":"publisher","unstructured":"C Pan, Q Li, and X Yao, 2024 \"Adversarial initialization with universal adversarial perturbation: a new approach to fast adversarial training,\" presented at the thirty-eighth conference on artificial intelligence, AAAI 2024, Vancouver, Canada. [Online]. Available: https:\/\/doi.org\/10.1609\/aaai.v38i19.30147","DOI":"10.1609\/aaai.v38i19.30147"},{"key":"1629_CR50","unstructured":"L Rice, E Wong, and JZ Kolter, 2020 \"Overfitting in adversarially robust deep learning,\" in Proceedings of the 37th international conference on machine learning, ICML 2020, vol. 119: JMLR.org, pp. 8093\u20138104"},{"key":"1629_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109229","volume":"136","author":"L Li","year":"2023","unstructured":"Li L, Spratling M (2023) Understanding and combating robust overfitting via input loss landscape analysis and regularization. Pattern Recognit 136:109229. https:\/\/doi.org\/10.1016\/j.patcog.2022.109229","journal-title":"Pattern Recognit"},{"key":"1629_CR52","unstructured":"VU Prabhu, DA Yap, J Xu, and J Whaley 2019 \"Understanding adversarial robustness through loss landscape geometries,\" in International conference on machine learning (ICML) workshops, 18"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01629-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01629-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01629-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:59:46Z","timestamp":1773172786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01629-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1629"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01629-8","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"10 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"65"}}