{"id":"https://openalex.org/W3199119343","doi":"https://doi.org/10.1109/trustcom53373.2021.00062","title":"Sybil Attacks and Defense on Differential Privacy based Federated Learning","display_name":"Sybil Attacks and Defense on Differential Privacy based Federated Learning","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3199119343","doi":"https://doi.org/10.1109/trustcom53373.2021.00062","mag":"3199119343"},"language":"en","primary_location":{"id":"doi:10.1109/trustcom53373.2021.00062","doi":"https://doi.org/10.1109/trustcom53373.2021.00062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom53373.2021.00062","pdf_url":null,"source":{"id":"https://openalex.org/S4363608016","display_name":"IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yupeng Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yupeng Jiang","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735403","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-2907-9811","observed_orcids":["https://orcid.org/0000-0002-2907-9811"]},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":"CN","type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Changchun University of Technology, Changchun, Jilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, Changchun, Jilin, China","institution_ids":["https://openalex.org/I4385474403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029669009","display_name":"Yipeng Zhou","orcid":"https://orcid.org/0000-0003-1533-0865","observed_orcids":["https://orcid.org/0000-0003-1533-0865"]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yipeng Zhou","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081182489","display_name":"Xi Zheng","orcid":"https://orcid.org/0000-0002-2572-2355","observed_orcids":["https://orcid.org/0000-0002-2572-2355"]},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xi Zheng","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8441,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88484611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9951000213623047,"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":0.9951000213623047,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.004800000227987766,"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/T10237","display_name":"Cryptography and Data Security","score":0.0,"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/sybil-attack","display_name":"Sybil attack","score":0.9950000047683716},{"id":"https://openalex.org/keywords/model-poisoning-attacks","display_name":"model poisoning","score":0.7279999852180481},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9940000176429749},{"id":"https://openalex.org/keywords/laplace-mechanism","display_name":"Laplace mechanism","score":0.7149999737739563},{"id":"https://openalex.org/keywords/privacy-budget","display_name":"privacy budget","score":0.5519999861717224},{"id":"https://openalex.org/keywords/model-convergence","display_name":"model convergence","score":0.4090000092983246}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.9337717294692993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131887316703796},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6289381384849548},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5369218587875366},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4788244068622589},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.446379691362381},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4352344870567322},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.424316942691803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34228894114494324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33289024233818054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21319010853767395},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/trustcom53373.2021.00062","doi":"https://doi.org/10.1109/trustcom53373.2021.00062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom53373.2021.00062","pdf_url":null,"source":{"id":"https://openalex.org/S4363608016","display_name":"IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7214548269","display_name":null,"funder_award_id":"LP190100676,DE180100950","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1520914943","https://openalex.org/W1873763122","https://openalex.org/W2112507308","https://openalex.org/W2490498838","https://openalex.org/W2541884796","https://openalex.org/W2752689052","https://openalex.org/W2771264586","https://openalex.org/W2774423163","https://openalex.org/W2784621220","https://openalex.org/W2789903762","https://openalex.org/W2789911054","https://openalex.org/W2804073516","https://openalex.org/W2810065831","https://openalex.org/W2883108656","https://openalex.org/W2903356604","https://openalex.org/W2913452160","https://openalex.org/W2936608441","https://openalex.org/W2946633206","https://openalex.org/W2965721472","https://openalex.org/W2970204870","https://openalex.org/W2990614164","https://openalex.org/W2995022099","https://openalex.org/W2996769125","https://openalex.org/W3015535799","https://openalex.org/W3022231501","https://openalex.org/W3082674854","https://openalex.org/W3084128899","https://openalex.org/W3137092842"],"related_works":["https://openalex.org/W3094551038","https://openalex.org/W6927227001","https://openalex.org/W4388470342","https://openalex.org/W4320481068","https://openalex.org/W2886444620","https://openalex.org/W4417355921","https://openalex.org/W4399147128","https://openalex.org/W4413332413","https://openalex.org/W4385412128","https://openalex.org/W4404006835"],"abstract_inverted_index":{"In":[0,94],"federated":[1,23,107],"learning,":[2],"machine":[3],"learning":[4,7,24,108],"and":[5,110,175,184,221],"deep":[6],"models":[8],"are":[9,75],"trained":[10],"globally":[11],"on":[12,68,103,114,140,181,227],"distributed":[13],"devices.":[14],"The":[15],"state-of-the-art":[16],"privacy-preserving":[17],"technique":[18],"in":[19,57,214],"the":[20,99,129,141,152,182,194,197,208,228,239,251],"context":[21],"of":[22,134,145,196,211,236,253],"is":[25,33,84],"user-level":[26],"differential":[27,82,104,135],"privacy.":[28],"However,":[29],"such":[30,41],"a":[31,150,203],"mechanism":[32,139],"vulnerable":[34],"to":[35,60,77,161,167,205],"some":[36,120],"specific":[37],"model":[38,63,72,90,115,143,154],"poisoning":[39,73],"attacks":[40,59,74,80,102,166,190,225],"as":[42,86,238],"Sybil":[43,58,79,101,147,224,255],"attacks.":[44,256],"A":[45],"malicious":[46],"adversary":[47],"could":[48],"create":[49],"multiple":[50],"fake":[51],"clients":[52,121,237],"or":[53,158],"collude":[54],"compromised":[55],"devices":[56],"mount":[61],"direct":[62],"updates":[64,91,144],"manipulation.":[65],"Recent":[66],"works":[67],"novel":[69],"defense":[70,171,248],"against":[71],"difficult":[76],"detect":[78],"when":[81],"privacy":[83,105,131,136],"utilized,":[85],"it":[87],"masks":[88],"clients'":[89],"with":[92,137],"perturbation.":[93],"this":[95],"work,":[96],"we":[97],"implement":[98],"first":[100],"based":[106,226],"architectures":[109],"show":[111,187],"their":[112],"impacts":[113],"convergence.":[116],"We":[117,163,200],"randomly":[118,233],"compromise":[119],"by":[122,128],"manipulating":[123],"different":[124],"noise":[125],"levels":[126],"reflected":[127],"local":[130,142],"budget":[132],"\u03b5":[133],"Laplace":[138],"these":[146],"clients.":[148],"As":[149],"result,":[151],"global":[153,198],"convergence":[155,195,218],"rates":[156],"decrease":[157],"even":[159],"leads":[160],"divergence.":[162],"apply":[164],"our":[165,189,223,247,254],"two":[168],"recent":[169],"aggregation":[170],"mechanisms,":[172],"called":[173],"Krum":[174],"Trimmed":[176],"Mean.":[177],"Our":[178,242],"evaluation":[179],"results":[180],"MNIST":[183],"CIFAR-10":[185],"datasets":[186],"that":[188,246],"effectively":[191,249],"slow":[192],"down":[193],"models.":[199],"then":[201],"propose":[202],"method":[204],"keep":[206],"monitoring":[207],"average":[209],"loss":[210,230],"all":[212],"participants":[213],"each":[215],"round":[216],"for":[217],"anomaly":[219],"detection":[220],"defend":[222],"training":[229],"reported":[231],"from":[232],"selected":[234],"sets":[235],"judging":[240],"panels.":[241],"empirical":[243],"study":[244],"demonstrates":[245],"mitigates":[250],"impact":[252]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-09-27T00:00:00"}