{"id":"https://openalex.org/W4415234006","doi":"https://doi.org/10.48550/arxiv.2507.18372","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","display_name":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4415234006","doi":"https://doi.org/10.48550/arxiv.2507.18372"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.18372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18372","pdf_url":"https://arxiv.org/pdf/2507.18372","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.18372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041100313","display_name":"George Wynne","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wynne, George","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041100313"],"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/T12401","display_name":"Scheduling and Timetabling Solutions","score":0.9218000173568726,"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"}},"topics":[{"id":"https://openalex.org/T12401","display_name":"Scheduling and Timetabling Solutions","score":0.9218000173568726,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9081000089645386,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7002999782562256},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.59170001745224},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5583000183105469},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.4262999892234802},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4041999876499176},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.38100001215934753},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.32350000739097595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7002999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215999722480774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.27950000762939453},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2776959682","wikidata":"https://www.wikidata.org/wiki/Q17005296","display_name":"Co-training","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.18372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18372","pdf_url":"https://arxiv.org/pdf/2507.18372","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.18372","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.18372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.18372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18372","pdf_url":"https://arxiv.org/pdf/2507.18372","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Publicly":[0],"releasing":[1],"the":[2,20,48,51,54,81,87],"specification":[3],"of":[4,31,53],"a":[5,28,43,61,68,84],"model":[6],"with":[7],"its":[8],"trained":[9],"parameters":[10],"means":[11],"an":[12],"adversary":[13],"can":[14],"attempt":[15],"to":[16,46],"reconstruct":[17],"information":[18],"about":[19],"training":[21,24,55],"data":[22,25,56,74],"via":[23,60],"reconstruction":[26],"attacks,":[27],"major":[29],"vulnerability":[30],"modern":[32],"machine":[33],"learning":[34],"methods.":[35],"This":[36],"paper":[37],"makes":[38],"three":[39],"primary":[40],"contributions:":[41],"establishing":[42],"mathematical":[44],"framework":[45,71],"express":[47],"problem,":[49],"characterising":[50],"features":[52],"that":[57],"are":[58],"vulnerable":[59],"maximum":[62],"mean":[63],"discrepancy":[64],"equivalance":[65],"and":[66,78],"outlining":[67],"score":[69],"matching":[70],"for":[72],"reconstructing":[73],"in":[75,86],"both":[76],"Bayesian":[77],"non-Bayesian":[79],"models,":[80],"former":[82],"is":[83],"first":[85],"literature.":[88]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}