{"id":"https://openalex.org/W4403487579","doi":"https://doi.org/10.3233/faia240736","title":"A Data-Driven Defense Against Edge-Case Model Poisoning Attacks on Federated Learning","display_name":"A Data-Driven Defense Against Edge-Case Model Poisoning Attacks on Federated Learning","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487579","doi":"https://doi.org/10.3233/faia240736"},"language":"en","primary_location":{"id":"doi:10.3233/faia240736","doi":"https://doi.org/10.3233/faia240736","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240736","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4403488923","display_name":"ECAI 2024"},"type":"book-chapter","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009272947","display_name":"Kiran Purohit","orcid":"https://orcid.org/0000-0002-5512-3441","observed_orcids":["https://orcid.org/0000-0002-5512-3441"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kiran Purohit","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103201369","display_name":"Soumi Das","orcid":"https://orcid.org/0000-0002-6933-5744","observed_orcids":["https://orcid.org/0000-0002-6933-5744"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumi Das","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046910575","display_name":"Sourangshu Bhattacharya","orcid":"https://orcid.org/0000-0001-5220-1881","observed_orcids":["https://orcid.org/0000-0001-5220-1881"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourangshu Bhattacharya","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024215125","display_name":"Santu Rana","orcid":"https://orcid.org/0000-0003-2247-850X","observed_orcids":["https://orcid.org/0000-0003-2247-850X"]},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Santu Rana","raw_affiliation_strings":["Deakin University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1394,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9388199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":97},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8422999978065491,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8422999978065491,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.15710000693798065,"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/T10400","display_name":"Network Security and Intrusion Detection","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/federated-learning","display_name":"federated learning","score":0.8859999775886536},{"id":"https://openalex.org/keywords/model-poisoning-attacks","display_name":"model poisoning","score":0.9869999885559082},{"id":"https://openalex.org/keywords/poisoning-defense","display_name":"poisoning defense","score":0.5400000214576721},{"id":"https://openalex.org/keywords/alternating-optimization","display_name":"alternating optimization","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5835012197494507},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5813032984733582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5397802591323853},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.44207730889320374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27862775325775146}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3233/faia240736","doi":"https://doi.org/10.3233/faia240736","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240736","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2305.02022","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.02022","pdf_url":"https://arxiv.org/pdf/2305.02022","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27663660","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_Data-Driven_Defense_Against_Edge-Case_Model_Poisoning_Attacks_on_Federated_Learning/27663660","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"doi:10.48550/arxiv.2305.02022","doi":"https://doi.org/10.48550/arxiv.2305.02022","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.02022","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.3233/faia240736","doi":"https://doi.org/10.3233/faia240736","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240736","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487579.pdf","grobid_xml":"https://content.openalex.org/works/W4403487579.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2748789698","https://openalex.org/W2774423163","https://openalex.org/W2990595670","https://openalex.org/W2996769125","https://openalex.org/W3095273258","https://openalex.org/W3138597937","https://openalex.org/W4376852246"],"related_works":["https://openalex.org/W3116740735","https://openalex.org/W4412830250","https://openalex.org/W4385567819","https://openalex.org/W4387185397","https://openalex.org/W6991135365","https://openalex.org/W4413146189","https://openalex.org/W4290948380","https://openalex.org/W3203600060","https://openalex.org/W6983527847","https://openalex.org/W7165121109"],"abstract_inverted_index":{"Federated":[0,156],"Learning":[1,157],"systems":[2],"are":[3,28,147],"increasingly":[4],"subjected":[5],"to":[6,31,37,76,86,184,218],"a":[7,21,38,64,73,88,108,117,129,220],"multitude":[8],"of":[9,24,66,116,132],"model":[10,92,111,124,145,171],"poisoning":[11,172],"attacks":[12,18,173],"from":[13],"clients.":[14],"Among":[15],"these,":[16],"edge-case":[17],"that":[19,112,166],"target":[20],"small":[22],"fraction":[23],"the":[25,57,98,114,133,142,155,186],"input":[26],"space":[27],"nearly":[29],"impossible":[30],"detect":[32],"using":[33,48,149],"existing":[34],"defenses,":[35],"leading":[36],"high":[39],"attack":[40,58,163,187,197,224],"success":[41,188,225],"rate.":[42,226],"We":[43],"propose":[44],"an":[45,49,150],"effective":[46],"defense":[47,51,61,99,212],"external":[50],"dataset,":[52],"which":[53,93],"provides":[54],"information":[55],"about":[56],"target.":[59],"The":[60,79,122,137],"dataset":[62,85,100],"contains":[63],"mix":[65],"poisoned":[67,89,102,138],"and":[68,141,199],"clean":[69],"examples,":[70],"with":[71],"only":[72],"few":[74,211,215],"known":[75],"be":[77],"clean.":[78,104],"proposed":[80],"method,":[81],"DataDefense,":[82],"uses":[83],"this":[84],"learn":[87],"data":[90,139],"detector":[91,140],"marks":[94],"each":[95],"example":[96],"in":[97,223],"as":[101,128,216],"or":[103],"It":[105],"also":[106],"learns":[107],"client":[109,118,134,143],"importance":[110,144],"estimates":[113],"probability":[115],"update":[119],"being":[120],"malicious.":[121],"global":[123],"is":[125,182],"then":[126],"updated":[127,148],"weighted":[130],"average":[131],"models\u2019":[135],"updates.":[136],"parameters":[146],"alternating":[151],"minimization":[152],"strategy":[153],"over":[154],"rounds.":[158],"Extensive":[159],"experiments":[160],"on":[161,195,204],"standard":[162,196],"scenarios":[164],"demonstrate":[165],"DataDefense":[167,181,208],"can":[168],"defend":[169],"against":[170],"where":[174],"other":[175],"state-of-the-art":[176],"defenses":[177],"fail.":[178],"In":[179],"particular,":[180],"able":[183],"reduce":[185],"rate":[189],"by":[190,200],"at":[191],"least":[192],"\u223c":[193],"40%":[194],"setups":[198],"more":[201],"than":[202],"80%":[203],"some":[205],"setups.":[206],"Furthermore,":[207],"requires":[209],"very":[210],"examples":[213],"(as":[214],"five)":[217],"achieve":[219],"near-optimal":[221],"reduction":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-18T00:00:00"}