{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:06:30Z","timestamp":1780765590768,"version":"3.54.1"},"reference-count":25,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T00:00:00Z","timestamp":1665532800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1712101"],"award-info":[{"award-number":["2020YFB1712101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072037"],"award-info":[{"award-number":["62072037"]}],"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":["U1936218"],"award-info":[{"award-number":["U1936218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Federated Learning (FL) is suitable for the application scenarios of distributed edge collaboration of the Internet of Things (IoT). It can provide data security and privacy, which is why it is widely used in the IoT applications such as Industrial IoT (IIoT). Latest research shows that the federated learning framework is vulnerable to poisoning attacks in the case of an active attack by the adversary. However, the existing backdoor attack methods are easy to be detected by the defence methods. To address this challenge, we focus on edge\u2010cloud synergistic FL clean\u2010label attacks. Unlike common backdoor attack, to ensure the attack's concealment, we add a small perturbation to realize the clean label attack by judging the cosine similarity between the gradient of the adversarial loss and the gradient of the normal training loss. In order to improve the attack success rate and robustness, the attack is implemented when the global model is about to converge. The experimental results verified that 1% of poisoned data could make an attack successful with a high probability. Our method maintains stealth while performing model poisoning attacks, and the average Peak Signal\u2010to\u2010Noise Ratio (PSNR) of poisoning images reaches over 30\u2009dB, and the average Structural SIMilarity (SSIM) is close to 0.93. Most importantly, our attack method can bypass the Byzantine aggregation defence.<\/jats:p>","DOI":"10.1111\/exsy.13161","type":"journal-article","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T09:15:10Z","timestamp":1665566110000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Clean\u2010label poisoning attacks on federated learning for <scp>IoT<\/scp>"],"prefix":"10.1111","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7574-4512","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology Beijing Institute of Technology  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-6246","authenticated-orcid":false,"given":"Jun","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology Beijing Institute of Technology  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5166-4873","authenticated-orcid":false,"given":"Thar","family":"Baker","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computing and Informatics University of Sharjah  Sharjah UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8467-0022","authenticated-orcid":false,"given":"Shuai","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology Beijing Institute of Technology  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6404-8853","authenticated-orcid":false,"given":"Yu\u2010an","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology Beijing Institute of Technology  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5094-7388","authenticated-orcid":false,"given":"Quanxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science Beijing Institute of Technology  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,10,12]]},"reference":[{"key":"e_1_2_9_2_1","first-page":"159","article-title":"Bullseye polytope: A scalable clean\u2010label poisoning attack with improved transferability","author":"Aghakhani H.","year":"2021","journal-title":"IEEE"},{"key":"e_1_2_9_3_1","first-page":"6900","article-title":"A survey on the edge computing for the internet of things","volume":"6","author":"Al\u2010Khafajiy M.","year":"2017","journal-title":"IEEE Access"},{"key":"e_1_2_9_4_1","first-page":"2938","article-title":"How to backdoor federated learning","author":"Bagdasaryan E.","year":"2020","journal-title":"Proceedings of the Twenty Third International Conference"},{"key":"e_1_2_9_5_1","first-page":"634","article-title":"Analyzing federated learning through an adversarial lens","author":"Bhagoji A. N.","year":"2019","journal-title":"PMLR"},{"key":"e_1_2_9_6_1","unstructured":"BurtonD. KenamondM. MorganN. CarneyT. &ShashkovM.An intersection based ALE scheme (xALE) for cell centered hydrodynamics (CCH). Paper presented at Talk at Multimat 2013 International Conference on Numerical Methods for Multi\u2010Material Fluid Flows. International Conference on Multimat.; September 2\u20136 2013; San Francisco. LA\u2010UR\u201013\u201026756.2."},{"key":"e_1_2_9_7_1","first-page":"12080","article-title":"Metapoison: Practical general\u2010purpose clean\u2010label data poisoning","volume":"33","author":"Damaskinos G.","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_2_9_8_1","first-page":"1605","article-title":"Local model poisoning attacks to {byzantine\u2010robust} federated learning","author":"Fang M.","year":"2020","journal-title":"USENIX Security"},{"key":"e_1_2_9_9_1","article-title":"Witches' brew: Industrial scale data poisoning via gradient matching","author":"Geiping J.","year":"2020","journal-title":"arXiv preprint arXiv:200902276"},{"key":"e_1_2_9_10_1","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Konecny J.","year":"2016","journal-title":"arXiv preprint arXiv:161005492"},{"key":"e_1_2_9_11_1","article-title":"Adaptive asynchronous federated learning in resource\u2010constrained edge computing","author":"Liu J.","year":"2021","journal-title":"IEEE Trans Mob Comput"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297477"},{"key":"e_1_2_9_13_1","first-page":"572","article-title":"Learning under p\u2010tampering attacks","author":"Mahloujifar S.","year":"2018","journal-title":"PMLR"},{"issue":"4","key":"e_1_2_9_14_1","first-page":"1","article-title":"Orchestrating the development lifecycle of machine learning\u2010based IoT applications: A taxonomy and survey","volume":"53","author":"Puthal D.","year":"2020","journal-title":"ACM Comput Surv"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2021.3051813"},{"key":"e_1_2_9_16_1","first-page":"6106","article-title":"Poison frogs! Targeted clean\u2010label poisoning attacks on neural networks","volume":"31","author":"Shafahi A.","year":"2018","journal-title":"NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2994596"},{"key":"e_1_2_9_19_1","first-page":"480","article-title":"Data poisoning attacks against federated learning systems","author":"Tolpegin V.","year":"2020","journal-title":"Springer"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.05.020"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.03.003"},{"issue":"2","key":"e_1_2_9_22_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3298981","article-title":"Federated machine learning: Concept and applications","volume":"184","author":"Yang Q.","year":"2019","journal-title":"ACM Trans Intell Syst Technol"},{"key":"e_1_2_9_23_1","first-page":"1","article-title":"A practical cross\u2010device federated learning framework over 5G networks","volume":"99","author":"Yang W.","year":"2022","journal-title":"IEEE Wirel Commun"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023126"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22644"},{"key":"e_1_2_9_26_1","article-title":"Group key agreement protocol among terminals of the intelligent information system for mobile edge computing","volume":"37","author":"Zhang Q.","year":"2021","journal-title":"Int J Intell Syst"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.13161","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.13161","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.13161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T03:29:23Z","timestamp":1746502163000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.13161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,12]]},"references-count":25,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["10.1111\/exsy.13161"],"URL":"https:\/\/doi.org\/10.1111\/exsy.13161","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,12]]},"assertion":[{"value":"2022-05-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e13161"}}