{"id":"https://openalex.org/W4416839012","doi":"https://doi.org/10.1016/j.knosys.2026.116594","title":"Fraud is not just rarity: A causal prototype attention approach to realistic synthetic oversampling","display_name":"Fraud is not just rarity: A causal prototype attention approach to realistic synthetic oversampling","publication_year":2026,"publication_date":"2026-07-07","ids":{"openalex":"https://openalex.org/W4416839012","doi":"https://doi.org/10.1016/j.knosys.2026.116594"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.116594","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116594","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0950705126013201/pdf","source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S0950705126013201/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114859545","display_name":"C Giusti","orcid":"https://orcid.org/0000-0002-7804-5570"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Giusti","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy"],"raw_orcid":"https://orcid.org/0009-0001-1284-6631","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060702304","display_name":"Luca Guarnera","orcid":"https://orcid.org/0000-0001-8315-351X"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Guarnera","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8315-351X","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083466950","display_name":"Mirko Casu","orcid":"https://orcid.org/0000-0001-6975-2241"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirko Casu","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6975-2241","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042746008","display_name":"Sebastiano Battiato","orcid":"https://orcid.org/0000-0001-6127-2470"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Battiato","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6127-2470","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Catania, Viale Andrea Doria 6, Catania, 95125, Sicily, Italy","institution_ids":["https://openalex.org/I39063666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060702304"],"corresponding_institution_ids":["https://openalex.org/I39063666"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":{"value":3130,"currency":"USD","value_usd":3130},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01842808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"350","issue":null,"first_page":"116594","last_page":"116594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9232000112533569,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9232000112533569,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.012799999676644802,"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/cluster-analysis","display_name":"Cluster analysis","score":0.5878000259399414},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5198000073432922},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45590001344680786},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4169999957084656},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.39329999685287476},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.382999986410141},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.3772999942302704},{"id":"https://openalex.org/keywords/latent-class-model","display_name":"Latent class model","score":0.36329999566078186},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3458999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6255999803543091},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.382999986410141},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C70727504","wikidata":"https://www.wikidata.org/wiki/Q1806878","display_name":"Latent class model","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.2630999982357025}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.knosys.2026.116594","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116594","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0950705126013201/pdf","source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.14706","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.14706","pdf_url":"https://arxiv.org/pdf/2507.14706","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.14706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.14706","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:10.1016/j.knosys.2026.116594","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116594","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0950705126013201/pdf","source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G507880695","display_name":null,"funder_award_id":"PE00000014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416839012.pdf","grobid_xml":"https://content.openalex.org/works/W4416839012.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"fraudulent":[1],"credit":[2],"card":[3],"transactions":[4],"remains":[5],"a":[6,117],"significant":[7],"challenge,":[8],"due":[9],"to":[10,33,63,67,125,140,149],"the":[11,19,41,87,114,196],"extreme":[12],"class":[13,43],"imbalance":[14],"in":[15,69,123],"real-world":[16,79],"data":[17],"and":[18,72,100,109,155,177,190,198],"often":[20],"subtle":[21],"patterns":[22],"that":[23,96,163],"separate":[24],"fraud":[25,205],"from":[26],"legitimate":[27],"activity.":[28],"Existing":[29],"research":[30],"commonly":[31],"attempts":[32],"address":[34],"this":[35,83,210],"by":[36],"generating":[37],"synthetic":[38],"samples":[39],"for":[40,204,209],"minority":[42],"using":[44],"approaches":[45],"such":[46,143],"as":[47,144,146,148],"GANs,":[48],"VAEs":[49],"(Variational":[50],"Autoencoders),":[51],"or":[52],"hybrid":[53],"generative":[54,151],"models.":[55],"However,":[56],"these":[57],"techniques,":[58],"particularly":[59],"when":[60],"applied":[61],"only":[62],"minority-class":[64],"data,":[65],"tend":[66],"result":[68],"overconfident":[70],"classifiers":[71],"poor":[73],"latent":[74,102,128,158,165,184],"cluster":[75,129,185],"separation,":[76],"ultimately":[77],"limiting":[78],"detection":[80],"performance.":[81],"In":[82],"study,":[84],"we":[85,110],"propose":[86],"Causal":[88],"Prototype":[89],"Attention":[90],"Classifier":[91],"(CPAC),":[92],"an":[93,173],"interpretable":[94],"architecture":[95],"promotes":[97],"class-aware":[98],"clustering":[99],"improved":[101,127,183],"space":[103],"structure":[104],"through":[105],"prototype-based":[106],"attention":[107],"mechanisms":[108],"couple":[111],"it":[112],"with":[113,154,167,182],"encoder":[115],"of":[116,175,179,200],"Variational":[118],"Autoencoder\u2013Generative":[119],"Adversarial":[120],"Network":[121],"(VAE-GAN)":[122],"order":[124],"achieve":[126],"separation":[130],"moving":[131],"beyond":[132],"post-hoc":[133],"sample":[134],"augmentation.":[135],"We":[136],"compared":[137],"CPAC-augmented":[138],"models":[139],"traditional":[141],"oversamplers,":[142],"SMOTE,":[145],"well":[147],"state-of-the-art":[150],"models,":[152],"both":[153],"without":[156],"CPAC-based":[157],"classifiers.":[159],"Our":[160],"results":[161],"show":[162],"classifier-guided":[164],"shaping":[166],"CPAC":[168],"delivers":[169],"superior":[170],"performance,":[171],"achieving":[172],"F1-score":[174],"93.74%":[176],"recall":[178],"92.85%,":[180],"along":[181],"separation.":[186],"Further":[187],"ablation":[188],"studies":[189],"visualizations":[191],"provide":[192],"deeper":[193],"insight":[194],"into":[195],"benefits":[197],"limitations":[199],"classifier-driven":[201],"representation":[202],"learning":[203],"detection.":[206],"The":[207],"codebase":[208],"work":[211],"will":[212],"be":[213],"available":[214],"at":[215],"final":[216],"submission.":[217]},"counts_by_year":[],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}