{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T04:18:35Z","timestamp":1784002715638,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62072482"],"award-info":[{"award-number":["62072482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnnls.2024.3379172","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T15:25:02Z","timestamp":1711553102000},"page":"5480-5493","source":"Crossref","is-referenced-by-count":12,"title":["Generalizable and Discriminative Representations for Adversarially Robust Few-Shot Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6232-9157","authenticated-orcid":false,"given":"Junhao","family":"Dong","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1007-8843","authenticated-orcid":false,"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-4679","authenticated-orcid":false,"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3080276"},{"key":"ref7","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref8","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Snell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3018506"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3011526"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083650"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082928"},{"key":"ref15","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. ICLR","author":"Szegedy"},{"key":"ref16","first-page":"125","article-title":"Adversarial examples are not bugs, they are features","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ilyas"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2984972"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3266702"},{"key":"ref21","first-page":"1","article-title":"Adversarially robust few-shot learning: A meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Goldblum"},{"key":"ref22","article-title":"Adversarial meta-learning","author":"Yin","year":"2018","journal-title":"arXiv:1806.03316"},{"key":"ref23","article-title":"On fast adversarial robustness adaptation in model-agnostic meta-learning","author":"Wang","year":"2021","journal-title":"arXiv:2102.10454"},{"key":"ref24","first-page":"1","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00882"},{"key":"ref26","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce"},{"key":"ref27","first-page":"1","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Oreshkin"},{"key":"ref28","first-page":"8","article-title":"MetaGAN: An adversarial approach to few-shot learning","volume-title":"Proc. NeurIPS","volume":"2","author":"Zhang"},{"key":"ref29","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2018","journal-title":"arXiv:1807.05960"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref31","first-page":"1","article-title":"MELR: Meta-learning via modeling episode-level relationships for few-shot learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Fei"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref33","article-title":"Self-supervised knowledge distillation for few-shot learning","author":"Rajasegaran","year":"2020","journal-title":"arXiv:2006.09785"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17021"},{"key":"ref35","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2963764"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref39","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref40","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref41","first-page":"1","article-title":"Intriguing properties of adversarial training at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref42","first-page":"1","article-title":"Geometry-aware instance-reweighted adversarial training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290532"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3244172"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3155975"},{"key":"ref46","first-page":"1","article-title":"Mitigating adversarial effects through randomization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3264699"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00095"},{"key":"ref49","article-title":"A simple approach to adversarial robustness in few-shot image classification","author":"Subramanya","year":"2022","journal-title":"arXiv:2204.05432"},{"key":"ref50","article-title":"Robust few-shot learning without using any adversarial samples","author":"Nayak","year":"2022","journal-title":"arXiv:2211.01598"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213755"},{"key":"ref52","first-page":"1","article-title":"A closer look at accuracy vs. robustness","volume-title":"Proc. NIPS","author":"Yang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00946"},{"key":"ref54","article-title":"Local reweighting for adversarial training","author":"Gao","year":"2021","journal-title":"arXiv:2106.15776"},{"key":"ref55","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. ICLR","author":"Goodfellow"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref57","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref58","article-title":"Meta-learning with differentiable closed-form solvers","author":"Bertinetto","year":"2018","journal-title":"arXiv:1805.08136"},{"key":"ref59","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref60","first-page":"1","article-title":"Robustbench: A standardized adversarial robustness benchmark","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Croce"},{"key":"ref61","first-page":"1","article-title":"IEPT: Instance-level and episode-level pretext tasks for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17277"},{"key":"ref63","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref64","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref65","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2016","journal-title":"arXiv:1611.01236"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"ref67","first-page":"1","article-title":"Adversarial robustness comparison of vision transformer and MLP-mixer to CNNs","volume-title":"Proc. 32nd Brit. Mach. Vis. Conf.","author":"Benz"},{"key":"ref68","first-page":"18599","article-title":"When adversarial training meets vision transformers: Recipes from training to architecture","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Mo"},{"issue":"11","key":"ref69","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","first-page":"1","article-title":"Robustness may be at odds with accuracy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tsipras"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/10479220.pdf?arnumber=10479220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:17Z","timestamp":1764959957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10479220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":70,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3379172","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}