{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:08:15Z","timestamp":1764184095434,"version":"3.46.0"},"reference-count":63,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62402029","62572502","62302539","62222201","U23A20304"],"award-info":[{"award-number":["62402029","62572502","62302539","62222201","U23A20304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hainan Provincial Natural Science Foundation Lingshui Li\u2019an International Education Innovation Experimental Zone Joint Project","award":["624LALH005"],"award-info":[{"award-number":["624LALH005"]}]},{"name":"National Cryptologic Science Fund of China","award":["2025NCSF02030"],"award-info":[{"award-number":["2025NCSF02030"]}]},{"name":"Beijing Natural Science Foundation","award":["L251041"],"award-info":[{"award-number":["L251041"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3633157","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:48:30Z","timestamp":1763146110000},"page":"12460-12475","source":"Crossref","is-referenced-by-count":0,"title":["FinBack: Infiltrating Backdoors into Gradient Compressors on Federated Learning"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5511-0720","authenticated-orcid":false,"given":"Xiangyun","family":"Tang","sequence":"first","affiliation":[{"name":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China"}]},{"given":"Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1277-4251","authenticated-orcid":false,"given":"Luyao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1867-0972","authenticated-orcid":false,"given":"Meng","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3366-7640","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-550X","authenticated-orcid":false,"given":"Yu","family":"Weng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-3490","authenticated-orcid":false,"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Konecn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3657284"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3079315"},{"key":"ref4","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref5","article-title":"BadNets: Identifying vulnerabilities in the machine learning model supply chain","author":"Gu","year":"2017","journal-title":"arXiv:1708.06733"},{"key":"ref6","article-title":"Can you really backdoor federated learning?","author":"Sun","year":"2019","journal-title":"arXiv:1911.07963"},{"key":"ref7","first-page":"2011","article-title":"FLAME: Taming backdoors in federated learning","volume-title":"Proc. 31st USENIX Secur. Symp.","author":"Nguyen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.10.113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA54385.2022.10032341"},{"key":"ref11","first-page":"2728","article-title":"Invariant aggregator for defending against federated backdoor attacks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref13","first-page":"3973","article-title":"Fedboost: A communication-efficient algorithm for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hamer"},{"key":"ref14","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate newton-type method","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"32","author":"Shamir"},{"key":"ref15","article-title":"SignSGD with majority vote is communication efficient and fault tolerant","volume-title":"arXiv:1810.05291","author":"Bernstein","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422337.3447837"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833647"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SPW59333.2023.00011"},{"key":"ref20","article-title":"A reputation mechanism is all you need: Collaborative fairness and adversarial robustness in federated learning","author":"Xu","year":"2020","journal-title":"arXiv:2011.10464"},{"key":"ref21","article-title":"BROADCAST: Reducing both stochastic and compression noise to robustify communication-efficient federated learning","author":"Zhu","year":"2021","journal-title":"arXiv:2104.06685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2022.23054"},{"key":"ref23","article-title":"Stochastic-sign SGD for federated learning with theoretical guarantees","author":"Jin","year":"2020","journal-title":"arXiv:2002.10940"},{"key":"ref24","first-page":"5830","article-title":"Dba: Distributed backdoor attacks against federated learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref25","first-page":"26429","article-title":"Neurotoxin: Durable backdoors in federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref26","article-title":"PerDoor: Persistent non-uniform backdoors in federated learning using adversarial perturbations","author":"Alam","year":"2022","journal-title":"arXiv:2205.13523"},{"key":"ref27","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Alistarh"},{"key":"ref28","article-title":"Efficient backdoor removal through natural gradient fine-tuning","author":"Karim","year":"2023","journal-title":"arXiv:2306.17441"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01615"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464809"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/242"},{"key":"ref33","first-page":"16070","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179401"},{"key":"ref38","first-page":"4157","article-title":"Lurking in the shadows: Unveiling stealthy backdoor attacks against personalized federated learning","volume-title":"Proc. 33rd USENIX Secur. Symp.","author":"Lyu"},{"key":"ref39","first-page":"61213","article-title":"A3fl: Adversarially adaptive backdoor attacks to federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3368754"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26083"},{"key":"ref42","article-title":"Mitigating sybils in federated learning poisoning","author":"Fung","year":"2018","journal-title":"arXiv:1808.04866"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3354736"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111660"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3354049"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3384846"},{"key":"ref48","first-page":"23274","article-title":"Dragonn: Distributed randomized approximate gradients of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3165268"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109517"},{"key":"ref52","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wangni"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2024.2358790"},{"key":"ref54","first-page":"3252","article-title":"Error feedback fixes SignSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Karimireddy"},{"key":"ref55","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/COINS57856.2023.10189281"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2021.3059958"},{"key":"ref58","first-page":"8253","article-title":"FetchSGD: Communication-efficient federated learning with sketching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rothchild"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671964"},{"key":"ref60","first-page":"119","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Blanchard"},{"journal-title":"arXiv:1808.04866","article-title":"Mitigating sybils in federated learning poisoning","author":"Fung","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref63","article-title":"Q-sparse: All large language models can be fully sparsely-activated","author":"Wang","year":"2024","journal-title":"arXiv:2407.10969"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11249444.pdf?arnumber=11249444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:03:10Z","timestamp":1764183790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3633157","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"type":"print","value":"1556-6013"},{"type":"electronic","value":"1556-6021"}],"subject":[],"published":{"date-parts":[[2025]]}}}