{"id":"https://openalex.org/W7161306629","doi":"https://doi.org/10.48550/arxiv.2605.14686","title":"ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators","display_name":"ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161306629","doi":"https://doi.org/10.48550/arxiv.2605.14686"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14686","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.14686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056807568","display_name":"Davide Scassola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scassola, Davide","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015229597","display_name":"Andrea Coser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coser, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029795923","display_name":"Sebastiano Saccani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saccani, Sebastiano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8921999931335449,"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":0.8921999931335449,"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/T11719","display_name":"Data Quality and Management","score":0.056699998676776886,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6675999760627747},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6572999954223633},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43689998984336853},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.2994000017642975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433000206947327},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6572999954223633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6097000241279602},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49480000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C2776945810","wikidata":"https://www.wikidata.org/wiki/Q17006654","display_name":"Data anonymization","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14686","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14686","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"data":[1,14,23,68,115],"sharing":[2],"under":[3],"privacy":[4,104],"constraints":[5],"is":[6,196],"increasingly":[7],"important":[8],"for":[9],"research":[10],"and":[11,65,113,143,161],"collaboration.":[12],"Synthetic":[13],"generators":[15],"(SDGs)":[16],"are":[17,50,86],"a":[18,39,102,127,146,152,167],"promising":[19],"solution,":[20],"but":[21,52,88],"synthetic":[22,137],"remains":[24],"vulnerable":[25],"to":[26,36,82,92,170],"attacks,":[27],"such":[28],"as":[29],"membership":[30],"inference":[31],"attacks":[32],"(MIAs),":[33],"which":[34,150],"aim":[35],"determine":[37],"whether":[38,126,145],"specific":[40],"record":[41,84,128,153],"was":[42,129],"part":[43],"of":[44,61],"the":[45,73,119,131],"training":[46,63,75,111,121,132],"data.":[47],"State-of-the-art":[48],"MIAs":[49,172],"powerful":[51],"impractical:":[53],"they":[54],"rely":[55],"on":[56],"shadow":[57],"modeling,":[58],"requiring":[59],"hundreds":[60],"SDG":[62,110],"runs,":[64],"need":[66],"auxiliary":[67],"several":[69],"times":[70],"larger":[71,117],"than":[72,118,124],"original":[74,120],"set.":[76,122],"Fast":[77],"proxy":[78],"metrics":[79],"like":[80],"distance":[81],"closest":[83],"(DCR)":[85],"efficient":[87],"have":[89],"limited":[90],"sensitivity":[91,168],"MIA":[93],"risk.":[94],"We":[95,178],"introduce":[96],"ReMIA":[97,134,165],"(Relative":[98],"Membership":[99],"Inference":[100],"Attack),":[101],"practical":[103],"metric":[105],"that":[106,164,181,187],"requires":[107],"only":[108],"two":[109,136,140],"runs":[112],"additional":[114],"no":[116],"Rather":[123],"predicting":[125],"in":[130],"set,":[133],"generates":[135],"datasets":[138,142,160],"from":[139],"source":[141,151],"measures":[144],"classifier":[147],"can":[148,183],"identify":[149],"came":[154],"from.":[155],"Experiments":[156],"across":[157],"multiple":[158],"tabular":[159],"SDGs":[162,182],"show":[163],"has":[166],"comparable":[169],"state-of-the-art":[171],"while":[173],"being":[174],"substantially":[175],"more":[176],"practical.":[177],"further":[179],"observe":[180],"achieve":[184],"privacy-utility":[185],"trade-offs":[186],"traditional":[188],"noise-based":[189],"anonymization":[190],"methods":[191],"do":[192],"not":[193],"match.":[194],"Code":[195],"available":[197],"at":[198],"https://github.com/aindo-com/remia.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-16T00:00:00"}