{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T07:22:49Z","timestamp":1770103369436,"version":"3.49.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402400"],"award-info":[{"award-number":["62402400"]}],"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":["62372386"],"award-info":[{"award-number":["62372386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["SWU-KQ23005"],"award-info":[{"award-number":["SWU-KQ23005"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025YFE0220300"],"award-info":[{"award-number":["2025YFE0220300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3655513","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:54:13Z","timestamp":1768856053000},"page":"1438-1453","source":"Crossref","is-referenced-by-count":0,"title":["EndPCA: Ensemble Defense With Provably Convergent Aggregation Against Poisoning Attacks in Federated Learning"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3003-8902","authenticated-orcid":false,"given":"Mingyue","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9123-4036","authenticated-orcid":false,"given":"Chenyu","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2227-9896","authenticated-orcid":false,"given":"Xuelian","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0445-0573","authenticated-orcid":false,"given":"Atul","family":"Sajjanhar","sequence":"additional","affiliation":[{"name":"Deakin University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8610-9936","authenticated-orcid":false,"given":"Zheng","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5109-9547","authenticated-orcid":false,"given":"Muneeb Ul","family":"Hassan","sequence":"additional","affiliation":[{"name":"Deakin University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1087-226X","authenticated-orcid":false,"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4327-1807","authenticated-orcid":false,"given":"Jialong","family":"Li","sequence":"additional","affiliation":[{"name":"Waseda Institute for Advanced Study, Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3501813"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00241"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548171"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007817"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3555618"},{"key":"ref6","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018","journal-title":"arXiv:1811.03604"},{"key":"ref7","volume-title":"Designing for Privacy","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3590765"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3570202"},{"key":"ref10","article-title":"Efficient blockchain-based steganography via backcalculating generative adversarial network","author":"Chen","year":"2025","journal-title":"arXiv:2506.16023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26083"},{"key":"ref12","first-page":"1467","article-title":"Poisoning attacks against support vector machines","volume-title":"Proc. ICML","author":"Biggio"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3490861"},{"key":"ref14","first-page":"1605","article-title":"Local model poisoning attacks to Byzantine-robust federated learning","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Fang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE55969.2022.00044"},{"key":"ref16","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. AISTATS","author":"Bagdasaryan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179401"},{"key":"ref18","first-page":"1","article-title":"DBA: Distributed backdoor attacks against federated learning","volume-title":"Proc. ICLR","author":"Xie"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2022.23156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16849"},{"key":"ref21","first-page":"3518","article-title":"The hidden vulnerability of distributed learning in byzantium","volume-title":"Proc. ICML","author":"Mhamdi"},{"key":"ref22","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. NeurIPS","volume":"30","author":"Blanchard"},{"key":"ref23","first-page":"1641","article-title":"Justinian\u2019s gaavernor: Robust distributed learning with gradient aggregation agent","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Pan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539231"},{"key":"ref25","first-page":"10495","article-title":"Zeno++: Robust fully asynchronous SGD","volume-title":"Proc. ICML","volume":"1","author":"Xie"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"ref27","article-title":"Federated unlearning with knowledge distillation","author":"Wu","year":"2022","journal-title":"arXiv:2201.09441"},{"key":"ref28","first-page":"301","article-title":"The limitations of federated learning in Sybil settings","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Fung"},{"key":"ref29","first-page":"1415","article-title":"FLAME: Taming backdoors in federated learning","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Nguyen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.4310\/SII.2009.v2.n3.a8"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref34","first-page":"6106","article-title":"Poison frogs! targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref35","first-page":"1299","article-title":"When does machine learning FAIL? Generalized transferability for evasion and poisoning attacks","volume-title":"Proc. 27th USENIX Secur. Symp. (USENIX Security)","author":"Suciu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000783"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3517395"},{"key":"ref38","first-page":"16070","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref39","article-title":"RFLBAT: A robust federated learning algorithm against backdoor attack","author":"Wang","year":"2022","journal-title":"arXiv:2201.03772"},{"key":"ref40","article-title":"BackdoorIndicator: Leveraging OOD data for proactive backdoor detection in federated learning","author":"Li","year":"2024","journal-title":"arXiv:2405.20862"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488743"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12132926"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3212174"},{"key":"ref44","first-page":"5636","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. ICML","author":"Yin"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00057"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179336"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3564835"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114186"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.104"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3292040.3219655"},{"key":"ref52","first-page":"8632","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Baruch"},{"key":"ref53","first-page":"261","article-title":"Fall of empires: Breaking Byzantine-tolerant SGD by inner product manipulation","volume-title":"Proc. UAI","author":"Xie"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.23233"},{"key":"ref56","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref57","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref58","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref59","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref60","first-page":"437","article-title":"A public domain dataset for human activity recognition using smartphones","volume-title":"Proc. ESANN","author":"Anguita"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38569-4"},{"key":"ref64","first-page":"11994","article-title":"Learning to confuse: Generating training time adversarial data with auto-encoder","volume-title":"Proc. NeurIPS","volume":"32","author":"Feng"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2663474.2663479"},{"key":"ref66","article-title":"Revisit, extend, and enhance hessian-free influence functions","author":"Yang","year":"2024","journal-title":"arXiv:2405.17490"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308.006"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11358404.pdf?arnumber=11358404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:43:24Z","timestamp":1770065004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3655513","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}