{"id":"https://openalex.org/W7141450371","doi":"https://doi.org/10.48550/arxiv.2603.24982","title":"LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization","display_name":"LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141450371","doi":"https://doi.org/10.48550/arxiv.2603.24982"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24982","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130749858","display_name":"Guang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Guang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039576301","display_name":"Ziye Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Ziye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130740305","display_name":"Yihang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130814541","display_name":"Changqing Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Changqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.8618000149726868,"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":0.8618000149726868,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0494999997317791,"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":0.025800000876188278,"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/generalization","display_name":"Generalization","score":0.8108000159263611},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7870000004768372},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8108000159263611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023999929428101},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7870000004768372},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24982","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":"doi:10.48550/arxiv.2603.24982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24982","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":"article"},"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":{"Task-agnostic":[0],"model":[1,20,48,58,82,171,177,182],"fingerprinting":[2,151],"has":[3],"recently":[4],"gained":[5],"increasing":[6],"attention":[7],"due":[8],"to":[9,12,95,198],"its":[10,60],"ability":[11],"provide":[13],"a":[14,34,39,92,112,169,200,208,217],"universal":[15],"framework":[16,152],"applicable":[17],"across":[18,230],"diverse":[19,47],"architectures":[21],"and":[22,38,46,59,62,79,87,124,190,206,225,244],"tasks.":[23],"The":[24],"current":[25],"state-of-the-art":[26],"method,":[27],"MetaV,":[28],"ensures":[29],"generalization":[30,136,156,242],"by":[31,116,179],"jointly":[32,129],"training":[33,86,186],"set":[35,172],"of":[36,52,100,110,187,203],"fingerprints":[37,123],"neural-network-based":[40],"global":[41,126],"verifier":[42,127,210],"using":[43],"two":[44,165],"large":[45,201],"sets:":[49],"one":[50],"composed":[51],"pirated":[53,189],"models":[54,72,101],"(i.e.,":[55],"the":[56,63,98,104,108,125,135,196],"protected":[57],"variants)":[61],"other":[64],"comprising":[65],"independently":[66,191],"trained":[67,192],"models.":[68,141],"However,":[69],"publicly":[70],"available":[71],"are":[73,128],"scarce":[74],"in":[75,120,240],"many":[76],"real-world":[77],"domains,":[78],"constructing":[80],"such":[81,204],"sets":[83],"requires":[84],"intensive":[85],"massive":[88],"computational":[89,160,245],"resources,":[90],"posing":[91],"significant":[93],"barrier":[94],"deployment.":[96],"Reducing":[97],"number":[99,202],"can":[102],"alleviate":[103],"overhead,":[105],"but":[106],"increases":[107],"risk":[109],"overfitting,":[111],"problem":[113],"further":[114],"exacerbated":[115],"MetaV's":[117],"entangled":[118],"design,":[119],"which":[121],"all":[122],"trained.":[130],"This":[131],"overfitting":[132],"issue":[133],"compromises":[134],"capability":[137],"for":[138],"verifying":[139],"unseen":[140],"In":[142],"this":[143],"paper,":[144],"we":[145],"propose":[146],"LiteGuard,":[147],"an":[148],"efficient":[149],"task-agnostic":[150],"that":[153,175,212,235],"attains":[154],"enhanced":[155],"while":[157],"significantly":[158],"lowering":[159],"cost.":[161],"Specifically,":[162],"LiteGuard":[163,236],"introduces":[164],"key":[166],"innovations:":[167],"(i)":[168],"checkpoint-based":[170],"augmentation":[173],"strategy":[174],"enriches":[176],"diversity":[178],"leveraging":[180],"intermediate":[181],"snapshots":[183],"captured":[184],"during":[185],"each":[188,214],"model,":[193],"thereby":[194,221],"alleviating":[195],"need":[197],"train":[199],"models,":[205],"(ii)":[207],"local":[209,219],"architecture":[211],"pairs":[213],"fingerprint":[215],"with":[216],"lightweight":[218],"verifier,":[220],"reducing":[222],"parameter":[223],"entanglement":[224],"mitigating":[226],"overfitting.":[227],"Extensive":[228],"experiments":[229],"five":[231],"representative":[232],"tasks":[233],"show":[234],"consistently":[237],"outperforms":[238],"MetaV":[239],"both":[241],"performance":[243],"efficiency.":[246]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-28T00:00:00"}