{"id":"https://openalex.org/W7214784458","doi":"https://doi.org/10.48550/arxiv.2609.33037","title":"Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction","display_name":"Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214784458","doi":"https://doi.org/10.48550/arxiv.2609.33037"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.33037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33037","pdf_url":"https://arxiv.org/pdf/2609.33037","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.33037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102518312","display_name":"Prasanjit Dubey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dubey, Prasanjit","raw_affiliation_strings":["School of Industrial and Systems Engineering , Georgia Institute of Technology , Atlanta , GA 30332 , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering , Georgia Institute of Technology , Atlanta , GA 30332 , U.S.A","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037375461","display_name":"Aritra Guha","orcid":"https://orcid.org/0000-0003-3866-2918","observed_orcids":["https://orcid.org/0000-0003-3866-2918"]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guha, Aritra","raw_affiliation_strings":["AT&T Chief Data Office"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Chief Data Office","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014880531","display_name":"Xiaoming Huo","orcid":"https://orcid.org/0000-0003-0101-1206","observed_orcids":["https://orcid.org/0000-0003-0101-1206"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huo, Xiaoming","raw_affiliation_strings":["School of Industrial and Systems Engineering , Georgia Institute of Technology , Atlanta , GA 30332 , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering , Georgia Institute of Technology , Atlanta , GA 30332 , U.S.A","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.8931000232696533,"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":0.8931000232696533,"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":0.07169999927282333,"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":0.004100000020116568,"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/byzantine-attacks","display_name":"Byzantine attacks","score":0.6940000057220459},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.972000002861023},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.33899998664855957},{"id":"https://openalex.org/keywords/medical-question-answering","display_name":"medical question answering","score":0.6940000057220459}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7161999940872192},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.7148000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691100001335144},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C2778217198","wikidata":"https://www.wikidata.org/wiki/Q556977","display_name":"Cutoff","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215999901294708},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.33037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33037","pdf_url":"https://arxiv.org/pdf/2609.33037","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.33037","doi":"https://doi.org/10.48550/arxiv.2609.33037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.33037","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":"pmh:oai:arXiv.org:2609.33037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33037","pdf_url":"https://arxiv.org/pdf/2609.33037","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214784458.pdf","grobid_xml":"https://content.openalex.org/works/W7214784458.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1553101044","https://openalex.org/W1999243577","https://openalex.org/W2059676361","https://openalex.org/W2140459664","https://openalex.org/W2767079719","https://openalex.org/W2890894339","https://openalex.org/W2962809812","https://openalex.org/W2964060211","https://openalex.org/W2970641574","https://openalex.org/W2996769125","https://openalex.org/W3035249419","https://openalex.org/W3162922479","https://openalex.org/W4252076394","https://openalex.org/W4252654521","https://openalex.org/W4361012985","https://openalex.org/W4378942327","https://openalex.org/W4385980132","https://openalex.org/W4389519591","https://openalex.org/W4391013606","https://openalex.org/W4391305741","https://openalex.org/W4399062487","https://openalex.org/W4401043055","https://openalex.org/W4401306886","https://openalex.org/W4402670290","https://openalex.org/W4412378237","https://openalex.org/W4416034051","https://openalex.org/W4416034993","https://openalex.org/W7155831340","https://openalex.org/W7160943434","https://openalex.org/W7162640095","https://openalex.org/W7162642549","https://openalex.org/W7162760278","https://openalex.org/W7214087792"],"related_works":["https://openalex.org/W7162760278","https://openalex.org/W7166643079","https://openalex.org/W4394646487","https://openalex.org/W7160388121","https://openalex.org/W4416034993","https://openalex.org/W7164383233","https://openalex.org/W7172020802","https://openalex.org/W7138880392","https://openalex.org/W7161798567","https://openalex.org/W7160635805"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"lets":[3],"language":[4,248],"models":[5,249],"answer":[6,79,185,214],"questions":[7,93],"more":[8,232,261],"accurately":[9],"by":[10,62,228],"consulting":[11],"relevant":[12],"documents.":[13],"Many":[14],"valuable":[15],"collections,":[16],"such":[17],"as":[18,250],"medical":[19,244],"records,":[20],"cannot":[21],"be":[22,57],"pooled":[23],"because":[24],"of":[25,100,163,212,279,287],"privacy":[26],"rules.":[27],"Federated":[28],"RAG":[29],"leaves":[30],"each":[31],"collection":[32],"with":[33,80,94,186,247,282],"its":[34,43,167],"owner,":[35],"or":[36,60,125],"node,":[37],"which":[38],"scores":[39,169],"candidate":[40,157],"answers":[41],"from":[42],"own":[44,168],"documents;":[45],"a":[46,74,81,85,89,105,156,296],"central":[47],"hub":[48,144],"combines":[49],"the":[50,77,128,134,138,150,179,183,187,194,201,210,215,224,229,257,283,290],"scores.":[51,70],"Some":[52],"nodes,":[53,101,165,251],"called":[54],"Byzantine,":[55],"may":[56,108],"compromised,":[58],"faulty,":[59],"misled":[61],"instructions":[63],"hidden":[64],"in":[65,88,111,140,170,190],"documents,":[66],"and":[67,114,154,246],"report":[68],"arbitrary":[69],"Conformal":[71],"prediction":[72],"returns":[73],"set":[75,87],"containing":[76],"correct":[78,184],"chosen":[82,188],"probability,":[83],"using":[84,166,200],"cutoff":[86],"calibration":[90,129,152],"step":[91,113],"on":[92,239],"known":[95],"answers.":[96],"An":[97],"unknown":[98],"group":[99,162],"no":[102,260],"larger":[103],"than":[104,235,264,277],"declared":[106,291],"bound,":[107],"misreport":[109],"both":[110,141,171],"this":[112],"at":[115,222],"query":[116],"time.":[117],"Existing":[118],"methods":[119,281],"assume":[120],"every":[121],"node":[122],"is":[123],"honest":[124,135,164,216],"protect":[126],"only":[127,158,227],"step.":[130],"We":[131,176],"observe":[132],"that":[133,178,231],"nodes":[136,148,196,217,220,233,262],"are":[137],"same":[139,151,202,284],"steps.":[142],"The":[143],"therefore":[145],"has":[146],"all":[147,288],"score":[149],"questions,":[153],"keeps":[155],"if":[159],"some":[160,252],"plausible":[161],"steps,":[172],"would":[173],"keep":[174],"it.":[175,271],"prove":[177],"resulting":[180],"sets":[181,207,255],"contain":[182],"probability":[189,230],"finite":[191],"samples,":[192],"whatever":[193],"Byzantine":[195],"report.":[197],"No":[198],"method":[199],"information":[203],"can":[204],"return":[205],"smaller":[206,276],"without":[208],"risking":[209],"loss":[211],"an":[213],"support.":[218],"If":[219],"fail":[221,234],"random,":[223],"guarantee":[225],"weakens":[226],"declared.":[236],"In":[237],"simulations,":[238],"real":[240],"question-answering":[241],"tasks":[242],"including":[243],"exams,":[245],"hijacked,":[253],"our":[254],"reached":[256],"target":[258],"whenever":[259],"misbehaved":[263],"declared,":[265],"while":[266],"plain":[267],"averaging":[268],"could":[269],"miss":[270],"They":[272],"were":[273],"also":[274],"clearly":[275],"those":[278],"simpler":[280],"protection,":[285],"most":[286],"when":[289],"bound":[292,298],"was":[293],"generous,":[294],"so":[295],"cautious":[297],"costs":[299],"little.":[300]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}