{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T01:12:53Z","timestamp":1773969173638,"version":"3.50.1"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302184"],"award-info":[{"award-number":["62302184"]}],"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":["62436003"],"award-info":[{"award-number":["62436003"]}],"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":["62376103"],"award-info":[{"award-number":["62376103"]}],"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":["62206102"],"award-info":[{"award-number":["62206102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019035","name":"Science and Technology Program of Hubei Province","doi-asserted-by":"publisher","award":["2024BAA008"],"award-info":[{"award-number":["2024BAA008"]}],"id":[{"id":"10.13039\/501100019035","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019035","name":"Science and Technology Program of Hubei Province","doi-asserted-by":"publisher","award":["2025BAB011"],"award-info":[{"award-number":["2025BAB011"]}],"id":[{"id":"10.13039\/501100019035","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3307900"],"award-info":[{"award-number":["2024YFC3307900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neunet.2025.108515","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T00:10:53Z","timestamp":1766621453000},"page":"108515","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Alleviating noise memorization for adversarially robust few-shot learning"],"prefix":"10.1016","volume":"197","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3473-2469","authenticated-orcid":false,"given":"Yiman","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-9041","authenticated-orcid":false,"given":"Yixiong","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-8778","authenticated-orcid":false,"given":"Xiaosen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1846-4941","authenticated-orcid":false,"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7627-4604","authenticated-orcid":false,"given":"Kun","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7791-5511","authenticated-orcid":false,"given":"Ruixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108515_bib0001","series-title":"International conference on machine learning","first-page":"10","article-title":"Sharp-MAML: Sharpness-aware model-agnostic meta learning","author":"Abbas","year":"2022"},{"issue":"7","key":"10.1016\/j.neunet.2025.108515_bib0002","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1109\/TMM.2020.2969784","article-title":"Towards improving robustness of deep neural networks to adversarial perturbations","volume":"22","author":"Amini","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108515_bib0003","series-title":"Proceedings of the 34th international conference on machine learning, ICML 2017, sydney, nsw, australia, 6\u201311 august 2017","first-page":"233","article-title":"A closer look at memorization in deep networks","volume":"vol. 70","author":"Arpit","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14493","article-title":"Improved few-shot visual classification","author":"Bateni","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0005","unstructured":"Bertinetto, L., Henriques, J. F., Torr, P. H. S., & Vedaldi, A. (2018). Meta-learning with differentiable closed-form solvers. arXiv preprint arXiv: 1805.08136."},{"key":"10.1016\/j.neunet.2025.108515_bib0006","series-title":"2017 IEEE symposium on security and privacy (sp)","first-page":"39","article-title":"Towards evaluating the robustness of neural networks","author":"Carlini","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0007","series-title":"International conference on learning representations","article-title":"Robust overfitting may be mitigated by properly learned smoothening","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2025.108515_bib0008","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/TMM.2021.3123813","article-title":"Mixer-based semantic spread for few-shot learning","volume":"25","author":"Cheng","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108515_bib0009","series-title":"International conference on machine learning","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","author":"Croce","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0010","series-title":"2009\u202fIEEE Conference on computer vision and pattern recognition","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2025.108515_bib0011","series-title":"Proceedings of the 34th international conference on machine learning, ICML 2017, Sydney, NSW, Australia, 6\u201311 august 2017","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume":"vol. 70","author":"Dinh","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9025","article-title":"Improving adversarially robust few-shot image classification with generalizable representations","author":"Dong","year":"2022"},{"key":"10.1016\/j.neunet.2025.108515_bib0013","series-title":"International conference on machine learning","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0014","unstructured":"Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020). Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv: 2010.01412."},{"key":"10.1016\/j.neunet.2025.108515_bib0015","unstructured":"Fu, C., Chen, H., Ruan, N., & Jia, W. (2020). Label smoothing and adversarial robustness. arXiv preprint arXiv: 2009.08233."},{"key":"10.1016\/j.neunet.2025.108515_bib0016","doi-asserted-by":"crossref","first-page":"1784","DOI":"10.1109\/TMM.2022.3162951","article-title":"Weakly supervised few-shot segmentation via meta-learning","volume":"25","author":"Gama","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108515_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3996","article-title":"Adversarially robust distillation","volume":"vol. 34","author":"Goldblum","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0018","first-page":"17886","article-title":"Adversarially robust few-shot learning: A meta-learning approach","volume":"33","author":"Goldblum","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0019","unstructured":"Gong, Z., Wang, W., & Ku, W.-S. (2017). Adversarial and clean data are not twins. arXiv preprint arXiv: 1704.04960."},{"key":"10.1016\/j.neunet.2025.108515_bib0020","unstructured":"Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv preprint arXiv: 1412.6572."},{"key":"10.1016\/j.neunet.2025.108515_bib0021","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"3018","article-title":"Low-shot visual recognition by shrinking and hallucinating features","author":"Hariharan","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0022","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"5S4","key":"10.1016\/j.neunet.2025.108515_bib0023","first-page":"427","article-title":"Deep learning and transfer learning approaches for image classification","volume":"7","author":"Krishna","year":"2019","journal-title":"International Journal of Recent Technology and Engineering (IJRTE)"},{"key":"10.1016\/j.neunet.2025.108515_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12576","article-title":"Boosting few-shot learning with adaptive margin loss","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0025","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017). Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv: 1706.06083."},{"key":"10.1016\/j.neunet.2025.108515_bib0026","unstructured":"Metzen, J. H., Genewein, T., Fischer, V., & Bischoff, B. (2017). On detecting adversarial perturbations. arXiv preprint arXiv: 1702.04267."},{"key":"10.1016\/j.neunet.2025.108515_bib0027","series-title":"Proceedings IEEE conference on computer vision and pattern recognition. CVPR 2000 (cat. no. PR00662)","first-page":"464","article-title":"Learning from one example through shared densities on transforms","volume":"vol. 1","author":"Miller","year":"2000"},{"key":"10.1016\/j.neunet.2025.108515_bib0028","first-page":"719","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume":"31","author":"Oreshkin","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0029","series-title":"Proceedings of the 2017\u202fACM on Asia conference on computer and communications security","first-page":"506","article-title":"Practical black-box attacks against machine learning","author":"Papernot","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0030","series-title":"2016\u202fIEEE Symposium on security and privacy (SP)","first-page":"582","article-title":"Distillation as a defense to adversarial perturbations against deep neural networks","author":"Papernot","year":"2016"},{"key":"10.1016\/j.neunet.2025.108515_bib0031","first-page":"14358","article-title":"Improving calibration through the relationship with adversarial robustness","volume":"34","author":"Qin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0032","series-title":"International conference on learning representations","article-title":"Optimization as a model for few-shot learning","author":"Ravi","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0033","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.108515_bib0034","first-page":"6747","article-title":"Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima","volume":"34","author":"Shi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0035","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0036","unstructured":"Song, Y., Kim, T., Nowozin, S., Ermon, S., & Kushman, N. (2017). PixelDefend: Leveraging generative models to understand and defend against adversarial examples. arXiv preprint arXiv: 1710.10766."},{"key":"10.1016\/j.neunet.2025.108515_bib0037","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7807","article-title":"Relating adversarially robust generalization to flat minima","author":"Stutz","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2025.108515_bib0038","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1109\/TPAMI.2020.3018506","article-title":"Meta-transfer learning through hard tasks","volume":"44","author":"Sun","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108515_bib0039","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"1199","article-title":"Learning to compare: Relation network for few-shot learning","author":"Sung","year":"2018"},{"key":"10.1016\/j.neunet.2025.108515_bib0040","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.neunet.2025.108515_bib0041","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013). Intriguing properties of neural networks. arXiv preprint arXiv: 1312.6199."},{"key":"10.1016\/j.neunet.2025.108515_bib0042","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, august 23\u201328, 2020, proceedings, part XIV 16","first-page":"266","article-title":"Rethinking few-shot image classification: A good embedding is all you need?","author":"Tian","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0043","unstructured":"Tram\u00e8r, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017). Ensemble adversarial training: Attacks and defenses. arXiv preprint arXiv: 1705.07204."},{"key":"10.1016\/j.neunet.2025.108515_bib0044","first-page":"3630","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0045","unstructured":"Wang, R., Xu, K., Liu, S., Chen, P.-Y., Weng, T.-W., Gan, C., & Wang, M. (2021). On fast adversarial robustness adaptation in model-agnostic meta-learning. arXiv preprint arXiv: 2102.10454."},{"key":"10.1016\/j.neunet.2025.108515_bib0046","series-title":"International conference on learning representations","article-title":"Improving adversarial robustness requires revisiting misclassified examples","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0047","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume":"33","author":"Wu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108515_bib0048","unstructured":"Yin, C., Tang, J., Xu, Z., & Wang, Y. (2018). Adversarial meta-learning. arXiv preprint arXiv: 1806.03316."},{"key":"10.1016\/j.neunet.2025.108515_bib0049","series-title":"5th international conference on learning representations, ICLR 2017, Toulon, France, april 24\u201326, 2017, conference track proceedings","article-title":"Understanding deep learning requires rethinking generalization","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2025.108515_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12203","article-title":"DeepEMD: Few-shot image classification with differentiable earth mover\u2019s distance and structured classifiers","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108515_bib0051","series-title":"International conference on machine learning","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108515_bib0052","series-title":"International conference on learning representations","article-title":"IEPT: Instance-level and episode-level pretext tasks for few-shot learning","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2025.108515_bib0053","first-page":"1","article-title":"ATZSL: Defensive zero-shot recognition in the presence of adversaries","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108515_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"20247","article-title":"Gradient norm aware minimization seeks first-order flatness and improves generalization","author":"Zhang","year":"2023"},{"issue":"2","key":"10.1016\/j.neunet.2025.108515_bib0055","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s11633-017-1053-3","article-title":"A survey on deep learning-based fine-grained object classification and semantic segmentation","volume":"14","author":"Zhao","year":"2017","journal-title":"International Journal of Automation and Computing"},{"key":"10.1016\/j.neunet.2025.108515_bib0056","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TMM.2020.2993952","article-title":"Attribute-guided feature learning for few-shot image recognition","volume":"23","author":"Zhu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108515_bib0057","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"16443","article-title":"Revisiting adversarial robustness distillation: Robust soft labels make student better","author":"Zi","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013966?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013966?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:31:19Z","timestamp":1773963079000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025013966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":57,"alternative-id":["S0893608025013966"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108515","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Alleviating noise memorization for adversarially robust few-shot learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108515","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108515"}}