{"id":"https://openalex.org/W7162428266","doi":"https://doi.org/10.48550/arxiv.2605.24008","title":"CAFD: Concept-Aware DNN Fault Detection using VLMs","display_name":"CAFD: Concept-Aware DNN Fault Detection using VLMs","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7162428266","doi":"https://doi.org/10.48550/arxiv.2605.24008"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24008","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":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.2605.24008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092657440","display_name":"Amin Abbasishahkoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abbasishahkoo, Amin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072142047","display_name":"Mahboubeh Dadkhah","orcid":"https://orcid.org/0000-0002-0436-8369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dadkhah, Mahboubeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137002703","display_name":"Lionel Briand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Briand, Lionel","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/T10028","display_name":"Topic Modeling","score":0.09809999912977219,"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/T10028","display_name":"Topic Modeling","score":0.09809999912977219,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09120000153779984,"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/T12127","display_name":"Software System Performance and Reliability","score":0.08839999884366989,"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/scalability","display_name":"Scalability","score":0.6036999821662903},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.5701000094413757},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.517300009727478},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43070000410079956},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4284999966621399},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667999863624573},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.5701000094413757},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4514999985694885},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24008","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":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.2605.24008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24008","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fault":[0,51,194],"detection":[1,61],"for":[2,153],"Deep":[3],"Neural":[4],"Networks":[5],"(DNNs)":[6],"has":[7],"received":[8],"increasing":[9],"attention":[10],"in":[11,42,193],"recent":[12],"years.":[13],"While":[14],"more":[15,139],"advanced":[16],"hybrid":[17],"approaches":[18],"have":[19],"been":[20],"proposed":[21],"to":[22,110],"combine":[23],"multiple":[24,66],"sources":[25,68],"of":[26,82,163,184,202],"information":[27,67],"and":[28,40,95,116,176,208],"outperform":[29],"earlier":[30],"techniques,":[31],"they":[32],"often":[33],"incur":[34],"substantial":[35],"computational":[36],"overhead,":[37],"limiting":[38],"scalability":[39],"practicality":[41],"real-world":[43],"settings.":[44],"In":[45],"this":[46,130],"paper,":[47],"we":[48],"introduce":[49],"Concept-Aware":[50],"Detection":[52,195],"(CAFD),":[53],"a":[54,78,96,181],"learning-based":[55],"approach":[56],"that":[57,120,146],"achieves":[58],"superior":[59],"fault":[60,141,155],"performance":[62],"by":[63],"effectively":[64],"integrating":[65],"while":[69],"maintaining":[70],"practical":[71],"efficiency.":[72],"Specifically,":[73],"CAFD":[74,132,188],"is":[75,123],"trained":[76],"using":[77],"carefully":[79],"selected":[80],"set":[81],"informative":[83],"features,":[84,94],"including":[85,178],"model-based":[86],"signals":[87],"derived":[88],"from":[89,114,134],"the":[90,118],"DNN's":[91],"outputs,":[92],"distance-based":[93],"novel":[97],"concept-based":[98],"feature,":[99,131],"called":[100],"Concept":[101],"Failure":[102],"Ratio":[103],"(CFR).":[104],"CFR":[105,147],"leverages":[106],"Vision-Language":[107],"Models":[108],"(VLMs)":[109],"extract":[111],"textual":[112],"concepts":[113],"images":[115],"quantify":[117],"likelihood":[119],"their":[121],"presence":[122],"associated":[124],"with":[125],"DNN":[126,154,174],"failures.":[127],"By":[128],"incorporating":[129],"benefits":[133],"complementary":[135],"semantic":[136],"information,":[137],"enabling":[138],"effective":[140,151],"detection.":[142,156],"Our":[143],"results":[144],"demonstrate":[145],"serves":[148],"as":[149],"an":[150,159],"indicator":[152],"We":[157],"conduct":[158],"extensive":[160],"empirical":[161],"evaluation":[162],"CAFD,":[164],"comparing":[165],"it":[166],"against":[167],"five":[168],"state-of-the-art":[169],"baselines":[170,192],"across":[171,204],"three":[172],"subject":[173],"models":[175],"datasets,":[177],"ImageNet.":[179],"Across":[180],"wide":[182],"range":[183],"constrained":[185],"selection":[186],"budgets,":[187],"consistently":[189],"outperforms":[190],"all":[191,205],"Rate":[196],"(FDR),":[197],"achieving":[198],"average":[199],"FDR":[200],"improvements":[201],"18.3%":[203],"investigated":[206],"subjects":[207],"budget":[209],"sizes.":[210]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}