{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T10:05:36Z","timestamp":1777025136474,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502262"],"award-info":[{"award-number":["61502262"]}],"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":["42201506"],"award-info":[{"award-number":["42201506"]}],"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":["62001262"],"award-info":[{"award-number":["62001262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3538891","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T19:14:37Z","timestamp":1738782877000},"page":"28628-28644","source":"Crossref","is-referenced-by-count":7,"title":["A Meta-Reinforcement Learning-Based Poisoning Attack Framework Against Federated Learning"],"prefix":"10.1109","volume":"13","author":[{"given":"Wei","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6356-8248","authenticated-orcid":false,"given":"Donglai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjian","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109492"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110424"},{"key":"ref5","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref9","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Geiping"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00989"},{"key":"ref11","first-page":"634","article-title":"Analyzing federated learning through an adversarial lens","volume-title":"Proc. Mach. Learn. Res.","volume":"97","author":"Bhagoji"},{"key":"ref12","first-page":"35007","article-title":"Learning to attack federated learning: A model-based reinforcement learning attack framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103270"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.02.025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.103936"},{"key":"ref16","first-page":"1","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Blanchard"},{"key":"ref17","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Yin"},{"key":"ref18","first-page":"66364","article-title":"IBA: Towards irreversible backdoor attacks in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Nguyen"},{"key":"ref19","first-page":"1","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Baruch"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121192"},{"key":"ref21","first-page":"1605","article-title":"Local model poisoning attacks to Byzantine-robust federated learning","volume-title":"Proc. 29th USENIX Secur. Symp. (USENIX Secur.)","author":"Fang"},{"key":"ref22","first-page":"261","article-title":"Fall of empires: Breaking Byzantine-tolerant SGD by inner product manipulation","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf., Proc. Mach. Learn. Res.","volume":"115","author":"Xie"},{"key":"ref23","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref25","first-page":"1467","article-title":"Poisoning attacks against support vector machines","volume-title":"Proc. 29th Int. Conf. Mach. Learn. (ICML)","author":"Biggio"},{"key":"ref26","first-page":"1","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Shafahi"},{"key":"ref27","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Bagdasaryan"},{"key":"ref28","first-page":"3521","article-title":"The hidden vulnerability of distributed learning in Byzantium","volume-title":"Proc. 35th Int. Conf. Mach. Learn., Proc. Mach. Learn. Res.","volume":"80","author":"El Mhamdi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"ref30","article-title":"IDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020","journal-title":"arXiv:2001.02610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","first-page":"1","article-title":"Scalable global optimization via local Bayesian optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eriksson"},{"key":"ref34","article-title":"The CMA evolution strategy: A tutorial","author":"Hansen","year":"2016","journal-title":"arXiv:1604.00772"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref36","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref37","volume-title":"Learning multiple layers of features from Tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"issue":"268","key":"ref39","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Fujimoto"},{"key":"ref41","article-title":"Can you really backdoor federated learning?","author":"Sun","year":"2019","journal-title":"arXiv:1911.07963"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10872904.pdf?arnumber=10872904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:41:18Z","timestamp":1740084078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10872904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3538891","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}