{"id":"https://openalex.org/W4409657530","doi":"https://doi.org/10.1145/3696410.3714728","title":"Provably Robust Federated Reinforcement Learning","display_name":"Provably Robust Federated Reinforcement Learning","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657530","doi":"https://doi.org/10.1145/3696410.3714728"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714728","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","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/10.1145/3696410.3714728","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056811906","display_name":"Minghong Fang","orcid":"https://orcid.org/0000-0002-1365-3911"},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minghong Fang","raw_affiliation_strings":["University of Louisville, Louisville, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xilong Wang","orcid":"https://orcid.org/0000-0003-1324-0225"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xilong Wang","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009102659","display_name":"Neil Zhenqiang Gong","orcid":"https://orcid.org/0000-0002-9900-9309"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Zhenqiang Gong","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056811906"],"corresponding_institution_ids":["https://openalex.org/I142740786"],"apc_list":null,"apc_paid":null,"fwci":16.2185,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98795856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994999766349792,"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":0.9994999766349792,"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/T10524","display_name":"Traffic control and management","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.989799976348877,"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/computer-science","display_name":"Computer science","score":0.7932142019271851},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7828551530838013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43878263235092163},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32646477222442627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932142019271851},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7828551530838013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43878263235092163},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32646477222442627}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714728","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714728","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714728","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2996144953","display_name":null,"funder_award_id":"W911NF2110182","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4503720401","display_name":null,"funder_award_id":"1937787","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G652313190","display_name":null,"funder_award_id":"2125977","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G777550411","display_name":null,"funder_award_id":"2131859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8377316191","display_name":null,"funder_award_id":"2112562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G976448290","display_name":"III: AF: Medium: Collaborative Research: Enabling Phylogenetic Inference for Modern Data Sets","funder_award_id":"2110182","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657530.pdf","grobid_xml":"https://content.openalex.org/works/W4409657530.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W151377110","https://openalex.org/W206679605","https://openalex.org/W1753414968","https://openalex.org/W1977655452","https://openalex.org/W2091565802","https://openalex.org/W2158782408","https://openalex.org/W2260756217","https://openalex.org/W2342662072","https://openalex.org/W2350778671","https://openalex.org/W2410099853","https://openalex.org/W2497473826","https://openalex.org/W2541884796","https://openalex.org/W2752689052","https://openalex.org/W2788115019","https://openalex.org/W2789911054","https://openalex.org/W2911450448","https://openalex.org/W2946633206","https://openalex.org/W2964312760","https://openalex.org/W2966002286","https://openalex.org/W2970204870","https://openalex.org/W2979766322","https://openalex.org/W2982316857","https://openalex.org/W2990614164","https://openalex.org/W2995164118","https://openalex.org/W3013816534","https://openalex.org/W3016207298","https://openalex.org/W3025019304","https://openalex.org/W3041107652","https://openalex.org/W3081055514","https://openalex.org/W3101686246","https://openalex.org/W3116666954","https://openalex.org/W3121342653","https://openalex.org/W3127520698","https://openalex.org/W3138153888","https://openalex.org/W3138597937","https://openalex.org/W3213895673","https://openalex.org/W4214690320","https://openalex.org/W4214717370","https://openalex.org/W4221129260","https://openalex.org/W4225571278","https://openalex.org/W4233210494","https://openalex.org/W4252654521","https://openalex.org/W4283313823","https://openalex.org/W4290948380","https://openalex.org/W4298113282","https://openalex.org/W4311165757","https://openalex.org/W4382935738","https://openalex.org/W4396757545","https://openalex.org/W4399835873","https://openalex.org/W4401597627","https://openalex.org/W4403046562","https://openalex.org/W4403752128","https://openalex.org/W4408750083","https://openalex.org/W6752600739","https://openalex.org/W6991135365"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Federated":[0],"reinforcement":[1],"learning":[2],"(FRL)":[3],"allows":[4],"agents":[5,133],"to":[6,30,59],"jointly":[7],"learn":[8],"a":[9,17,130,149,160],"global":[10,123,141],"decision-making":[11],"policy":[12,75],"under":[13],"the":[14,72,88,146,168,182],"guidance":[15],"of":[16,74,90,132],"central":[18],"server.":[19],"While":[20],"FRL":[21,41,103],"has":[22],"advantages,":[23],"its":[24],"decentralized":[25],"design":[26],"makes":[27],"it":[28],"prone":[29],"poisoning":[31,199],"attacks.":[32,116,200],"To":[33,95],"mitigate":[34],"this,":[35],"Byzantine-robust":[36,54,189],"aggregation":[37,137],"techniques":[38,55],"tailored":[39],"for":[40,148,163,171],"have":[42],"been":[43],"introduced.":[44],"Yet,":[45],"in":[46],"our":[47,60,82,113,192],"work,":[48],"we":[49,99],"reveal":[50],"that":[51,69,105,181],"these":[52,93,97],"current":[53],"are":[56],"not":[57],"immune":[58],"newly":[61,114],"introduced":[62],"Normalized":[63,83,183],"attack.":[64],"Distinct":[65],"from":[66],"previous":[67],"attacks":[68],"targeted":[70],"enlarging":[71],"distance":[73],"updates":[76],"before":[77],"and":[78,112,191],"after":[79],"an":[80,101],"attack,":[81],"attack":[84,184],"emphasizes":[85],"on":[86,159],"maximizing":[87],"angle":[89],"deviation":[91],"between":[92],"updates.":[94],"counter":[96],"threats,":[98],"develop":[100],"ensemble":[102,118,193],"approach":[104,194],"is":[106,127,156],"provably":[107],"secure":[108],"against":[109,198],"both":[110],"known":[111],"proposed":[115],"Our":[117,174],"method":[119],"involves":[120],"training":[121],"multiple":[122],"policies,":[124],"where":[125],"each":[126],"learnt":[128],"by":[129],"group":[131],"using":[134],"any":[135],"foundational":[136],"rule.":[138],"These":[139],"well-trained":[140],"policies":[142],"then":[143],"individually":[144],"predict":[145],"action":[147,155,165],"specific":[150],"test":[151],"state.":[152],"The":[153],"ultimate":[154],"chosen":[157],"based":[158],"majority":[161],"vote":[162],"discrete":[164],"systems":[166],"or":[167],"geometric":[169],"median":[170],"continuous":[172],"ones.":[173],"experimental":[175],"results":[176],"across":[177],"different":[178],"settings":[179],"show":[180],"can":[185],"greatly":[186],"disrupt":[187],"non-ensemble":[188],"methods,":[190],"offers":[195],"substantial":[196],"resistance":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}