{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:14:31Z","timestamp":1778948071100,"version":"3.51.4"},"reference-count":47,"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":[{"name":"Australia Research Council funding ARC","award":["LP200200084"],"award-info":[{"award-number":["LP200200084"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3558581","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:18:56Z","timestamp":1744132736000},"page":"4525-4540","source":"Crossref","is-referenced-by-count":2,"title":["Extracting Private Training Data in Federated Learning From Clients"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7180-4268","authenticated-orcid":false,"given":"Jiaheng","family":"Wei","sequence":"first","affiliation":[{"name":"School of Accounting, Information System and Supply Chain, RMIT University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5611-3483","authenticated-orcid":false,"given":"Yanjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9330-2662","authenticated-orcid":false,"given":"Leo","family":"Yu Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Brisbane, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1355-3870","authenticated-orcid":false,"given":"Chao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Accounting, Information System and Supply Chain, RMIT University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Brisbane, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4688-7674","authenticated-orcid":false,"given":"Kok-Leong","family":"Ong","sequence":"additional","affiliation":[{"name":"School of Accounting, Information System and Supply Chain, RMIT University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2189-7801","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-0831","authenticated-orcid":false,"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref2","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.02527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref5","first-page":"4774","article-title":"Deep leakage from gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Mu"},{"key":"ref6","first-page":"16937","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Geiping"},{"key":"ref7","first-page":"8712","article-title":"Dreaming to distill: Data-free knowledge transfer via DeepInversion","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yin"},{"key":"ref8","first-page":"16332","article-title":"See through gradients: Image batch recovery via GradInversion","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yin"},{"key":"ref9","article-title":"IDLG: Improved deep leakage from gradients","author":"Zhao","year":"2020","journal-title":"arXiv:2001.02610"},{"key":"ref10","article-title":"Fishing for user data in large-batch federated learning via gradient magnification","author":"Wen","year":"2022","journal-title":"arXiv:2202.00580"},{"key":"ref11","article-title":"Robbing the fed: Directly obtaining private data in federated learning with modified models","author":"Fowl","year":"2021","journal-title":"arXiv:2110.13057"},{"key":"ref12","article-title":"When the curious abandon honesty: Federated learning is not private","author":"Boenisch","year":"2021","journal-title":"arXiv:2112.02918"},{"key":"ref13","first-page":"29898","article-title":"Gradient inversion with generative image prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Jeon"},{"key":"ref14","first-page":"493","article-title":"BatchCrypt: Efficient homomorphic encryption for cross-silo federated learning","volume-title":"Proc. 2020 USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3592800"},{"key":"ref16","first-page":"8107","article-title":"Analyzing and improving the image quality of StyleGAN","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Karras"},{"key":"ref17","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Blanchard"},{"key":"ref18","first-page":"3521","article-title":"The hidden vulnerability of distributed learning in Byzantium","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"El Mhamdi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"ref20","first-page":"1605","article-title":"Local model poisoning attacks to Byzantine-robust federated learning","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Fang"},{"key":"ref21","article-title":"Generalized Byzantine-tolerant SGD","author":"Xie","year":"2018","journal-title":"arXiv:1802.10116"},{"key":"ref22","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yin"},{"key":"ref23","first-page":"8635","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Baruch"},{"key":"ref24","first-page":"1","article-title":"Manipulating the Byzantine: Optimizing model poisoning attacks and defenses for federated learning","volume-title":"Proc. Netw. Distrib. Syst. Secur. Symp.","author":"Shejwalkar"},{"key":"ref25","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref26","first-page":"16070","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref27","first-page":"634","article-title":"Analyzing federated learning through an adversarial lens","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Bhagoji"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01462"},{"key":"ref29","article-title":"Plug & play attacks: Towards robust and flexible model inversion attacks","author":"Struppek","year":"2022","journal-title":"arXiv:2201.12179"},{"key":"ref30","article-title":"R-GAP: Recursive gradient attack on privacy","author":"Zhu","year":"2020","journal-title":"arXiv:2010.07733"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3564625.3564658"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140451"},{"key":"ref33","article-title":"Model inversion attack against transfer learning: Inverting a model without accessing it","author":"Ye","year":"2022","journal-title":"arXiv:2203.06570"},{"key":"ref34","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref35","volume-title":"Tiny Imagenet","author":"Mnmoustafa","year":"2017"},{"key":"ref36","article-title":"Caltech-256 object category dataset","author":"Griffin","year":"2007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref42","first-page":"10697","article-title":"Deduplicating training data mitigates privacy risks in language models","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Kandpal"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00063"},{"key":"ref45","article-title":"LDP-FL: Practical private aggregation in federated learning with local differential privacy","author":"Sun","year":"2020","journal-title":"arXiv:2007.15789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3378679.3394533"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3317870"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/10955239.pdf?arnumber=10955239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T17:02:06Z","timestamp":1746550926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3558581","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}