{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:02:31Z","timestamp":1740132151859,"version":"3.37.3"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFF0725100"],"award-info":[{"award-number":["2023YFF0725100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3375287","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T17:54:08Z","timestamp":1710438848000},"page":"5905-5920","source":"Crossref","is-referenced-by-count":0,"title":["FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8266-4561","authenticated-orcid":false,"given":"Hanlin","family":"Gu","sequence":"first","affiliation":[{"name":"WeBank AI Lab, WeBank, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8162-7096","authenticated-orcid":false,"given":"Lixin","family":"Fan","sequence":"additional","affiliation":[{"name":"WeBank AI Lab, WeBank, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6740-9204","authenticated-orcid":false,"given":"XingXing","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5059-8360","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref2","first-page":"4613","article-title":"Byzantine stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref3","first-page":"1","article-title":"Byzantine-resilient non-convex stochastic gradient descent","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Allen-Zhu"},{"key":"ref4","first-page":"8635","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baruch"},{"key":"ref5","first-page":"1","article-title":"SignSGD with majority vote is communication efficient and fault tolerant","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bernstein"},{"key":"ref6","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Blanchard"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1939-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517819"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"journal-title":"Proc. Int. Workshop Trustable, Verifiable Auditable Federated Learn. Conjunc. AAAI","article-title":"Byzantine-resilient federated learning via gradient memorization","author":"Chen","key":"ref10"},{"key":"ref11","first-page":"903","article-title":"DRACO: Byzantine-resilient distributed training via redundant gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref13","first-page":"1145","article-title":"Asynchronous Byzantine machine learning (the case of SGD)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Damaskinos"},{"key":"ref14","first-page":"2478","article-title":"Byzantine-resilient high-dimensional SGD with local iterations on heterogeneous data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Data"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/17M1126680"},{"key":"ref16","first-page":"1","article-title":"Distributed momentum for Byzantine-resilient stochastic gradient descent","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Mhamdi"},{"key":"ref17","first-page":"1605","article-title":"Local model poisoning attacks to Byzantine-Robust federated learning","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Fang"},{"article-title":"Byzantine machine learning made easy by resilient averaging of momentums","year":"2022","author":"Farhadkhani","key":"ref18"},{"article-title":"Robust federated learning in a heterogeneous environment","year":"2019","author":"Ghosh","key":"ref19"},{"key":"ref20","first-page":"3521","article-title":"The hidden vulnerability of distributed learning in byzantium","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guerraoui"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/acc50511.2021.9483067"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"article-title":"Byzantine-robust decentralized learning via self-centered clipping","year":"2022","author":"He","key":"ref23"},{"article-title":"SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size","year":"2016","author":"Iandola","key":"ref24"},{"volume-title":"Algorithms for Clustering Data","year":"1988","author":"Jain","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"article-title":"Byzantine-robust learning on heterogeneous datasets via bucketing","year":"2020","author":"Karimireddy","key":"ref27"},{"key":"ref28","first-page":"5311","article-title":"Learning from history for Byzantine robust optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3335772.3335936"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Lenet-5, convolutional neural networks","year":"2015","author":"LeCun","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icde53745.2022.00077"},{"article-title":"Communication efficient decentralized training with multiple local updates","year":"2019","author":"Li","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref37","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1140\/epjb\/e2004-00124-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/2980539.2980649"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054377"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2022.3153135"},{"article-title":"Mitigating Byzantine attacks in federated learning","year":"2020","author":"Prakash","key":"ref42"},{"article-title":"DETOX: A redundancy-based framework for faster and more robust gradient aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rajput","key":"ref43"},{"article-title":"ByGARS: Byzantine SGD with arbitrary number of attackers","year":"2020","author":"Regatti","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1063\/1.5040897"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054676"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833647"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2010\/10\/P10020"},{"key":"ref51","first-page":"508","article-title":"Auror: Defending against poisoning attacks in collaborative deep learning systems","volume-title":"Proc. 32nd Annu. Conf. Comput. Secur. Appl.","author":"Shen"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref53","first-page":"14615","article-title":"Election coding for distributed learning: Protecting signsgd against Byzantine attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0378-4754(91)90038-5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/30918"},{"article-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref57"},{"article-title":"Generalized byzantine-tolerant SGD","year":"2018","author":"Xie","key":"ref58"},{"article-title":"Zeno: Byzantine-suspicious stochastic gradient descent","year":"2018","author":"Xie","key":"ref59"},{"key":"ref60","first-page":"261","article-title":"Fall of empires: Breaking Byzantine-tolerant SGD by inner product manipulation","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Xie"},{"key":"ref61","first-page":"10495","article-title":"Zeno: Robust fully asynchronous SGD","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029245"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref64","first-page":"11751","article-title":"BASGD: Buffered asynchronous SGD for byzantine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref65","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yin"},{"key":"ref66","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref67","first-page":"1601","article-title":"Self-tuning spectral clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zelnik-Manor"},{"key":"ref68","first-page":"493","article-title":"$\\lbrace${BatchCrypt $\\rbrace$}: Efficient homomorphic encryption for $\\lbrace${ Cross-Silo$\\rbrace$} federated learning","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539231"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10465649.pdf?arnumber=10465649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:46:18Z","timestamp":1723052778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10465649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":70,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3375287","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}