{"id":"https://openalex.org/W4407569678","doi":"https://doi.org/10.48550/arxiv.2502.07977","title":"RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent","display_name":"RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent","publication_year":2025,"publication_date":"2025-02-11","ids":{"openalex":"https://openalex.org/W4407569678","doi":"https://doi.org/10.48550/arxiv.2502.07977"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.07977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07977","pdf_url":"https://arxiv.org/pdf/2502.07977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.07977","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100664794","display_name":"Cheng Fang","orcid":"https://orcid.org/0000-0001-7293-9082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061333650","display_name":"Rishabh Dixit","orcid":"https://orcid.org/0000-0002-2649-7524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dixit, Rishabh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028718006","display_name":"Waheed U. Bajwa","orcid":"https://orcid.org/0000-0003-4406-5263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bajwa, Waheed U.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034370705","display_name":"Mert G\u00fcrb\u00fczbalaban","orcid":"https://orcid.org/0000-0002-0575-2450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gurbuzbalaban, Mert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4547632336616516},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.45116356015205383},{"id":"https://openalex.org/keywords/consensus-conference","display_name":"Consensus conference","score":0.4369235038757324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19635340571403503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4547632336616516},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.45116356015205383},{"id":"https://openalex.org/C3017605391","wikidata":"https://www.wikidata.org/wiki/Q1021509","display_name":"Consensus conference","level":2,"score":0.4369235038757324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19635340571403503},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.07977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07977","pdf_url":"https://arxiv.org/pdf/2502.07977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.07977","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.07977","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.07977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07977","pdf_url":"https://arxiv.org/pdf/2502.07977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1892760057","display_name":null,"funder_award_id":"CNS-2148104","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1983408797","display_name":"SHF: Small: Communication-Efficient Distributed Algorithms for Machine Learning","funder_award_id":"1814888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2408348303","display_name":null,"funder_award_id":"CCF-1814888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2736230042","display_name":"CIF: Small: Distributed Machine Learning in the Age of Fast Data Streams","funder_award_id":"1907658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3855261351","display_name":null,"funder_award_id":"N00014-21-1-2244","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5213350891","display_name":null,"funder_award_id":"CCF-1907658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7354933906","display_name":"RINGS: REALTIME: Resilient Edge-cloud Autonomous Learning with Timely Inferences","funder_award_id":"2148104","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407569678.pdf","grobid_xml":"https://content.openalex.org/works/W4407569678.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Empirical":[0],"risk":[1],"minimization":[2],"(ERM)":[3],"is":[4],"a":[5,53,158,205],"cornerstone":[6],"of":[7,160,166,220,230],"modern":[8],"machine":[9],"learning":[10,27,117,149],"(ML),":[11],"supported":[12],"by":[13,203],"advances":[14],"in":[15,49],"optimization":[16,123],"theory":[17],"that":[18,63],"ensure":[19,177],"efficient":[20,65],"solutions":[21],"with":[22],"provable":[23],"algorithmic":[24,191],"and":[25,32,39,66,192,199,211,228,237],"statistical":[26,178,193],"rates.":[28],"Privacy,":[29],"memory,":[30],"computation,":[31],"communication":[33,90,132],"constraints":[34],"necessitate":[35],"data":[36],"collection,":[37],"processing,":[38],"storage":[40],"across":[41,232],"network-connected":[42],"devices.":[43],"In":[44],"many":[45],"applications,":[46],"networks":[47],"operate":[48],"decentralized":[50,60,148],"settings":[51],"where":[52,134],"central":[54],"server":[55],"cannot":[56],"be":[57,127,138],"assumed,":[58],"requiring":[59],"ML":[61],"algorithms":[62],"are":[64],"resilient.":[67],"Decentralized":[68],"learning,":[69],"however,":[70],"faces":[71],"significant":[72],"challenges,":[73],"including":[74],"an":[75,122],"increased":[76],"attack":[77,233],"surface.":[78],"This":[79],"paper":[80],"focuses":[81],"on":[82],"the":[83,161,218,226],"man-in-the-middle":[84],"(MITM)":[85],"attack,":[86],"wherein":[87],"adversaries":[88],"exploit":[89],"vulnerabilities":[91],"to":[92,101,126,157,176,216],"inject":[93],"malicious":[94],"updates":[95],"during":[96],"training,":[97],"potentially":[98],"causing":[99],"models":[100],"deviate":[102],"from":[103],"their":[104],"intended":[105],"ERM":[106,201],"solutions.":[107],"To":[108],"address":[109],"this":[110],"challenge,":[111],"we":[112],"propose":[113],"RESIST":[114,184,231],"(Resilient":[115],"dEcentralized":[116],"using":[118],"conSensus":[119],"gradIent":[120],"deScenT),":[121],"algorithm":[124],"designed":[125],"robust":[128,147,212],"against":[129],"adversarially":[130,146],"compromised":[131],"links,":[133],"transmitted":[135],"information":[136],"may":[137],"arbitrarily":[139],"altered":[140],"before":[141],"being":[142],"received.":[143],"Unlike":[144],"existing":[145],"methods,":[150,236],"which":[151],"often":[152],"(i)":[153],"guarantee":[154],"convergence":[155,168,194],"only":[156],"neighborhood":[159],"solution,":[162],"(ii)":[163],"lack":[164],"guarantees":[165],"linear":[167],"for":[169,195],"strongly":[170,196],"convex":[171],"problems,":[172],"or":[173],"(iii)":[174],"fail":[175],"consistency":[179],"as":[180],"sample":[181],"sizes":[182],"grow,":[183],"overcomes":[185],"all":[186],"three":[187],"limitations.":[188],"It":[189],"achieves":[190],"convex,":[197],"Polyak-Lojasiewicz,":[198],"nonconvex":[200],"problems":[202],"employing":[204],"multistep":[206],"consensus":[207],"gradient":[208],"descent":[209],"framework":[210],"statistics-based":[213],"screening":[214,235],"methods":[215],"mitigate":[217],"impact":[219],"MITM":[221],"attacks.":[222],"Experimental":[223],"results":[224],"demonstrate":[225],"robustness":[227],"scalability":[229],"strategies,":[234],"loss":[238],"functions.":[239]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}