{"id":"https://openalex.org/W7154447485","doi":"https://doi.org/10.48550/arxiv.2604.12307","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","display_name":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154447485","doi":"https://doi.org/10.48550/arxiv.2604.12307"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12307","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":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.2604.12307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133711257","display_name":"Ruiyang Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Ruiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133693960","display_name":"Qi Zhang","orcid":"https://orcid.org/0009-0005-4616-7791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133685617","display_name":"Yaowen Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005852517","display_name":"Zhaofan Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Zhaofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009066619","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0002-3871-1954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133695744","display_name":"Zhongjiang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zhongjiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133676584","display_name":"Xuelong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xuelong","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":0.5516999959945679,"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":0.5516999959945679,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.26980000734329224,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.060600001364946365,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7534999847412109},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6579999923706055},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6371999979019165},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5169000029563904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3894999921321869},{"id":"https://openalex.org/keywords/visual-inspection","display_name":"Visual inspection","score":0.3569999933242798},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.683899998664856},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509000062942505},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6371999979019165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5169000029563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4959000051021576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3894999921321869},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12307","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.12307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12307","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4068397283554077}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,68,136],"proliferation":[1],"of":[2,12,70,77,85,123],"highly":[3],"realistic":[4],"AI-Generated":[5,165],"Image":[6,166],"(AIGI)":[7],"has":[8],"necessitated":[9],"the":[10,33,45,74,82,89,108,111,118,124,130,143,147,158,162,169],"development":[11],"practical":[13],"detection":[14,26,62,144],"methods.":[15],"While":[16],"current":[17],"AIGI":[18,64,134],"detectors":[19],"perform":[20],"admirably":[21],"on":[22,117],"clean":[23],"datasets,":[24],"their":[25],"performance":[27],"frequently":[28],"decreases":[29],"when":[30],"deployed":[31],"\"in":[32],"wild\",":[34],"where":[35],"images":[36],"are":[37],"subjected":[38],"to":[39,59,105,132,141],"unpredictable,":[40],"complex":[41],"distortions.":[42,67],"To":[43],"resolve":[44],"critical":[46],"vulnerability,":[47],"we":[48,99,128],"propose":[49],"a":[50,78,93],"novel":[51],"LoRA-based":[52],"Pairwise":[53],"Training":[54],"(LPT)":[55],"strategy":[56,72],"designed":[57],"specifically":[58],"achieve":[60,133],"robust":[61],"for":[63],"under":[65],"severe":[66],"core":[69],"our":[71,155],"involves":[73],"targeted":[75],"finetuning":[76],"visual":[79,120,125],"foundation":[80,126],"model,":[81,127],"deliberate":[83],"simulation":[84],"data":[86],"distribution":[87,109],"during":[88],"training":[90,96,138],"phase,":[91],"and":[92,102,113,149],"unique":[94],"pairwise":[95,137],"process.":[97],"Specifically,":[98],"introduce":[100],"distortion":[101],"size":[103],"simulations":[104],"better":[106],"fit":[107],"from":[110],"validation":[112],"test":[114],"sets.":[115],"Based":[116],"strong":[119],"representation":[121],"capability":[122],"finetune":[129],"model":[131],"detection.":[135],"is":[139],"utilized":[140],"improve":[142],"via":[145],"decoupling":[146],"generalization":[148],"robustness":[150],"optimization.":[151],"Experiments":[152],"show":[153],"that":[154],"approach":[156],"secured":[157],"3th":[159],"placement":[160],"in":[161,168],"NTIRE":[163],"Robust":[164],"Detection":[167],"Wild":[170],"challenge":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-16T00:00:00"}