{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:30:44Z","timestamp":1775503844063,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"13","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"\u201cPioneer\u201d and \u201cLeading Goose\u201d R&D Program of Zhejiang, China","award":["2024C03288"],"award-info":[{"award-number":["2024C03288"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61602408"],"award-info":[{"award-number":["61602408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LMS25F020007"],"award-info":[{"award-number":["LMS25F020007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,7,1]]},"DOI":"10.1109\/jiot.2025.3558627","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T18:00:13Z","timestamp":1744048813000},"page":"25136-25147","source":"Crossref","is-referenced-by-count":3,"title":["CBPF: A Novel Method for Filtering Poisoned Data Based on Composite Backdoor Attacks"],"prefix":"10.1109","volume":"12","author":[{"given":"Hanfeng","family":"Xia","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Zhejiang Gongshang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2908-8651","authenticated-orcid":false,"given":"Haibo","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Zhejiang Gongshang University, Hangzhou, China"}]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand"}]},{"given":"Yiru","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Zhejiang Gongshang University, Hangzhou, China"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology, Zhejiang Gongshang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3172939"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909068"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00038"},{"key":"ref9","first-page":"17258","article-title":"Topological detection of trojaned neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zheng"},{"key":"ref10","first-page":"1","article-title":"Detecting backdoor attacks on deep neural networks by activation clustering","volume-title":"Proc. Workshop Artif. Intell. Saf. Co-Located 33rd AAAI Conf. Artif. Intell.","author":"Chen"},{"key":"ref11","first-page":"1541","article-title":"Demon in the variant: Statistical analysis of DNNs for robust backdoor contamination detection","volume-title":"Proc. 30th USENIX Security Symp. (USENIX Security)","author":"Tang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359790"},{"key":"ref13","first-page":"8011","article-title":"Spectral signatures in backdoor attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Tran"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5040\/9781350250307-0201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00390"},{"key":"ref16","first-page":"14900","article-title":"Anti-backdoor learning: Training clean models on poisoned data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref17","first-page":"1","article-title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00426"},{"key":"ref19","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"Chen","year":"2017","journal-title":"arXiv:1712.05526"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01465"},{"key":"ref21","first-page":"1","article-title":"WaNet-imperceptible warping-based backdoor attack","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nguyen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802997"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423362"},{"key":"ref25","first-page":"1","article-title":"Revisiting the assumption of latent separability for backdoor defenses","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Qi"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01615"},{"key":"ref27","first-page":"1","article-title":"Distilling cognitive backdoor patterns within an image","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref28","first-page":"1","article-title":"SCALE-UP: An efficient black-box input-level backdoor detection via analyzing scaled prediction consistency","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref29","first-page":"1685","article-title":"Towards a proactive ML approach for detecting backdoor poison samples","volume-title":"Proc. 32nd USENIX Security Symp.","author":"Qi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref31","first-page":"16913","article-title":"Adversarial neuron pruning purifies backdoored deep models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wu"},{"key":"ref32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"ref35","volume-title":"Tiny ImageNet visual recognition challenge","author":"Le","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11045559\/10954977.pdf?arnumber=10954977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:09:35Z","timestamp":1771362575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10954977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":36,"journal-issue":{"issue":"13"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3558627","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]}}}