{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:29:55Z","timestamp":1773170995106,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502346"],"award-info":[{"award-number":["62502346"]}],"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":["U2441240"],"award-info":[{"award-number":["U2441240"]}],"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":["62441238"],"award-info":[{"award-number":["62441238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education Humanities and Social Sciences Project","award":["24JDSZ3073"],"award-info":[{"award-number":["24JDSZ3073"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2026.3652456","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"3988-4004","source":"Crossref","is-referenced-by-count":0,"title":["Armor: Shielding Unlearnable Examples Against Data Augmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2190-8117","authenticated-orcid":false,"given":"Xueluan","family":"Gong","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"given":"Yuji","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1382-0679","authenticated-orcid":false,"given":"Yanjiao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University, Hangzhou, China"}]},{"given":"Haocheng","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-265X","authenticated-orcid":false,"given":"Yiming","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"given":"Mengyuan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"given":"Shuaike","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8967-8525","authenticated-orcid":false,"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSEC.2018.2888775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414862"},{"issue":"1","key":"ref3","first-page":"9885","article-title":"A group-theoretic framework for data augmentation","volume":"21","author":"Chen","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","article-title":"LowKey: Leveraging adversarial attacks to protect social media users from facial recognition","author":"Cherepanova","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00025"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","article-title":"Imagenette: A smaller subset of 10 easily classified classes from imagenet","year":"2019"},{"key":"ref10","article-title":"Preventing unauthorized use of proprietary data: Poisoning for secure dataset release","author":"Fowl","year":"2021"},{"key":"ref11","first-page":"30339","article-title":"Adversarial examples make strong poisons","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fowl","year":"2021"},{"key":"ref12","article-title":"Robust unlearnable examples: Protecting data against adversarial learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3211013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.004.2100867"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583224"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01459"},{"key":"ref18","article-title":"Unlearnable examples: Making personal data unexploitable","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326398"},{"key":"ref20","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2020"},{"key":"ref21","first-page":"2651","article-title":"Swift: Super-fast and robust privacy-preserving machine learning","volume-title":"Proc. USENIX Secur. Symp.","author":"Koti","year":"2021"},{"key":"ref22","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3224044"},{"key":"ref24","article-title":"Fast autoaugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim","year":"2019"},{"key":"ref25","article-title":"Going grayscale: The road to understanding and improving unlearnable examples","author":"Liu","year":"2021"},{"key":"ref26","first-page":"22473","article-title":"Image shortcut squeezing: Countering perturbative availability poisons with compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475290"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.gltp.2022.04.020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3453108"},{"key":"ref33","article-title":"FenceBox: A platform for defeating adversarial examples with data augmentation techniques","author":"Qiu","year":"2020"},{"key":"ref34","article-title":"Data poisoning won\u2019t save you from facial recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Radiya-Dixit","year":"2022"},{"key":"ref35","first-page":"29935","article-title":"Data augmentation can improve robustness","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rebuffi","year":"2021"},{"key":"ref36","article-title":"Transferable unlearnable examples","author":"Ren","year":"2022"},{"key":"ref37","first-page":"1589","article-title":"Fawkes: Protecting privacy against unauthorized deep learning models","volume-title":"Proc. USENIX Secur. Symp.","author":"Shan","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2289457"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1198\/10618600152418584"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62328-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01096-5"},{"key":"ref45","article-title":"Improving adversarial robustness requires revisiting misclassified examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2019"},{"key":"ref46","first-page":"2237","article-title":"PatchGuard: A provably robust defense against adversarial patches via small receptive fields and masking","volume-title":"Proc. USENIX Secur. Symp.","author":"Xiang","year":"2021"},{"key":"ref47","first-page":"12230","article-title":"Neural tangent generalization attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60239-0_19"},{"key":"ref49","article-title":"You only propagate once: Accelerating adversarial training via maximal principle","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang","year":"2019"},{"key":"ref50","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref51","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref52","article-title":"Deep autoaugment","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Zheng","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11345171.pdf?arnumber=11345171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:56Z","timestamp":1773106496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3652456","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}