{"id":"https://openalex.org/W4396843697","doi":"https://doi.org/10.1145/3589335.3651503","title":"Exploring Representational Similarity Analysis to Protect Federated Learning from Data Poisoning","display_name":"Exploring Representational Similarity Analysis to Protect Federated Learning from Data Poisoning","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843697","doi":"https://doi.org/10.1145/3589335.3651503"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651503","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651503","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103239631","display_name":"Gengxiang Chen","orcid":"https://orcid.org/0009-0007-6945-8844"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gengxiang Chen","raw_affiliation_strings":["Sun Yat-Sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399848","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-0517-2392"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070017771","display_name":"Ahmed M. Abdelmoniem","orcid":"https://orcid.org/0000-0002-1374-1882"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed M. Abdelmoniem","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050820825","display_name":"Linlin You","orcid":"https://orcid.org/0000-0001-6287-8095"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin You","raw_affiliation_strings":["Sun Yat-Sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103239631"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":3.6261,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93542802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.972000002861023,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7225663661956787},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6068147420883179},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38602587580680847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3580658435821533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225663661956787},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6068147420883179},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38602587580680847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580658435821533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589335.3651503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651503","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651503","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843697.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2002427601","https://openalex.org/W2112796928","https://openalex.org/W3126365018","https://openalex.org/W3198262235","https://openalex.org/W4205488455","https://openalex.org/W4224322855","https://openalex.org/W4224937317","https://openalex.org/W4381886281","https://openalex.org/W4385079041","https://openalex.org/W4385573575"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"a":[1,73,130],"paradigm":[2],"that":[3,79,114],"preserves":[4],"privacy,":[5],"Federated":[6],"Learning":[7],"(FL)":[8],"enables":[9],"distributed":[10,59],"clients":[11],"to":[12,28],"cooperatively":[13],"train":[14],"global":[15,104],"models":[16,101,121],"using":[17],"local":[18,34,100,120],"datasets.":[19],"However,":[20],"this":[21],"approach":[22],"also":[23],"provides":[24],"opportunities":[25],"for":[26],"adversaries":[27],"compromise":[29],"system":[30],"stability":[31],"by":[32,94],"contaminating":[33],"data,":[35],"such":[36],"as":[37],"through":[38],"Label-Flipping":[39,126],"Attacks":[40,127],"(LFAs).":[41],"In":[42],"addressing":[43],"these":[44],"security":[45],"challenges,":[46],"most":[47],"existing":[48],"defense":[49,77],"strategies":[50],"presume":[51],"the":[52,86,96,103],"presence":[53],"of":[54,88],"an":[55],"independent":[56],"and":[57,75,102,122],"identically":[58],"(IID)":[60],"environment,":[61],"resulting":[62],"in":[63,129],"suboptimal":[64],"performance":[65],"under":[66],"Non-IID":[67,131],"conditions.":[68],"This":[69,91],"paper":[70],"introduces":[71],"RSim-FL,":[72],"novel":[74],"pragmatic":[76],"mechanism":[78],"incorporates":[80],"Representational":[81],"Similarity":[82],"Analysis":[83],"(RSA)":[84],"into":[85],"detection":[87],"malevolent":[89],"updates.":[90],"is":[92],"achieved":[93],"calculating":[95],"similarity":[97],"between":[98],"uploaded":[99],"model.":[105],"The":[106],"evaluation,":[107],"conducted":[108],"against":[109],"five":[110],"state-of-the-art":[111],"baselines,":[112],"demonstrates":[113],"RSim-FL":[115],"can":[116],"accurately":[117],"identify":[118],"malicious":[119],"effectively":[123],"mitigate":[124],"divergent":[125],"(LFAs)":[128],"setting.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}