{"id":"https://openalex.org/W7163389807","doi":"https://doi.org/10.48550/arxiv.2606.03925","title":"Adaptive Causal Alignment for High-Confidence Adversarial Training","display_name":"Adaptive Causal Alignment for High-Confidence Adversarial Training","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163389807","doi":"https://doi.org/10.48550/arxiv.2606.03925"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03925","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.2606.03925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137740518","display_name":"Zhiming Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Zhiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137744589","display_name":"Kejia Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kejia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137796873","display_name":"Yingxin Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Yingxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137722346","display_name":"Junwei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Junwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041234756","display_name":"Juanjuan Weng","orcid":"https://orcid.org/0000-0003-0825-2272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Juanjuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137732101","display_name":"Shaozi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shaozi","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6761000156402588,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6761000156402588,"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":0.20499999821186066,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04410000145435333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/overfitting","display_name":"Overfitting","score":0.7778000235557556},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6403999924659729},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6186000108718872},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5974000096321106},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5770999789237976},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.5559999942779541},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5346999764442444},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5310999751091003},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5281999707221985},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.47940000891685486}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7778000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456000208854675},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6403999924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6115000247955322},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03925","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.2606.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03925","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Inverse":[0],"adversarial":[1],"training":[2],"leverages":[3],"high-confidence":[4],"predictions":[5],"to":[6,22,65,99,127],"stabilize":[7],"robust":[8,157],"learning,":[9],"yet":[10],"we":[11,72],"uncover":[12],"a":[13,39,45,50,79,84,89,94,118],"critical":[14],"paradox:":[15],"high":[16],"confidence":[17],"often":[18],"stems":[19],"from":[20],"overfitting":[21],"non-causal":[23],"background":[24],"correlations":[25],"rather":[26],"than":[27],"intrinsic":[28],"object":[29],"semantics.":[30],"Our":[31],"investigation":[32],"reveals":[33],"that":[34,82,140],"visual":[35],"context":[36,102],"functions":[37],"as":[38,43,61],"dual-natured":[40],"signal,":[41],"serving":[42],"either":[44],"necessary":[46],"supportive":[47],"prior":[48],"or":[49],"spurious":[51],"confounder.":[52],"This":[53],"insight":[54],"renders":[55],"existing":[56],"blind":[57],"suppression":[58],"strategies":[59],"flawed,":[60],"they":[62],"inevitably":[63],"lead":[64],"severe":[66],"Feature":[67],"Loss.":[68],"To":[69],"resolve":[70],"this,":[71],"propose":[73],"High-Confidence":[74],"Causally":[75],"Aligned":[76],"Training":[77],"(HICAT),":[78],"unified":[80],"framework":[81],"establishes":[83],"Semantic":[85],"Equilibrium.":[86],"Operating":[87],"on":[88,134],"``Measure-Debias-Align''":[90],"pipeline,":[91],"HICAT":[92,141],"integrates":[93],"Learnable":[95],"Background-Bias":[96],"Estimator":[97],"(LBBE)":[98],"adaptively":[100],"diagnose":[101],"utility.":[103],"Guided":[104],"by":[105,117],"this":[106],"diagnosis,":[107],"an":[108],"Adaptive":[109],"Debiasing":[110],"mechanism":[111],"performs":[112],"surgical":[113],"logit":[114],"rectification,":[115],"complemented":[116],"geometrically":[119],"grounded":[120],"Foreground":[121],"Logit":[122],"Orthogonal":[123],"Enhancement":[124],"(FLOE)":[125],"loss":[126],"enforce":[128],"rigorous":[129],"feature":[130],"disentanglement.":[131],"Extensive":[132],"experiments":[133],"CIFAR-10,":[135],"CIFAR-100,":[136],"and":[137,151],"ImageNet-1K":[138],"demonstrate":[139],"consistently":[142],"improves":[143],"over":[144],"matched":[145],"baselines":[146],"across":[147],"diverse":[148],"architectures":[149],"(CNNs":[150],"ViTs)":[152],"while":[153],"significantly":[154],"reducing":[155],"the":[156],"generalization":[158],"gap.":[159]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}