{"id":"https://openalex.org/W7204265540","doi":"https://doi.org/10.48550/arxiv.2608.23984","title":"Source-Face Authenticity Detection for 3D Gaussian Heads Reconstructed from a Single Portrait: A Benchmark and Dedicated Detector","display_name":"Source-Face Authenticity Detection for 3D Gaussian Heads Reconstructed from a Single Portrait: A Benchmark and Dedicated Detector","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204265540","doi":"https://doi.org/10.48550/arxiv.2608.23984"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23984","pdf_url":"https://arxiv.org/pdf/2608.23984","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129681605","display_name":"Yujie Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Yujie","raw_affiliation_strings":["Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125553616","display_name":"Zijian Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Zijian","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143267302","display_name":"Yan Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Yan","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125405144","display_name":"Jun Lan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan, Jun","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134140031","display_name":"Jianfu Zhang","orcid":"https://orcid.org/0000-0002-2673-5860","observed_orcids":["https://orcid.org/0000-0002-2673-5860"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jianfu","raw_affiliation_strings":["Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9667999744415283,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9667999744415283,"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/T11448","display_name":"Face recognition and analysis","score":0.02630000002682209,"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/T10828","display_name":"Biometric Identification and Security","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/face-forgery-detection","display_name":"face forgery detection","score":0.7360000014305115},{"id":"https://openalex.org/keywords/identity-verification","display_name":"identity verification","score":0.6639999747276306},{"id":"https://openalex.org/keywords/face-privacy","display_name":"face privacy","score":0.9779999852180481},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5059999823570251},{"id":"https://openalex.org/keywords/multi-view-contrastive-learning","display_name":"multi-view contrastive learning","score":0.9769999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C29168087","wikidata":"https://www.wikidata.org/wiki/Q1026711","display_name":"Blob detection","level":5,"score":0.26030001044273376},{"id":"https://openalex.org/C3020376581","wikidata":"https://www.wikidata.org/wiki/Q16866784","display_name":"Single stage","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23984","pdf_url":"https://arxiv.org/pdf/2608.23984","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23984","doi":"https://doi.org/10.48550/arxiv.2608.23984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23984","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23984","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23984","pdf_url":"https://arxiv.org/pdf/2608.23984","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204265540.pdf","grobid_xml":"https://content.openalex.org/works/W7204265540.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154705669","https://openalex.org/W7081979820","https://openalex.org/W1988165558","https://openalex.org/W7154627800","https://openalex.org/W7160408604","https://openalex.org/W4286779522","https://openalex.org/W7159891816","https://openalex.org/W3197039127","https://openalex.org/W7117979325","https://openalex.org/W4415059314"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,30],"single-image":[3],"3D":[4,37],"Gaussian":[5],"head":[6],"reconstruction":[7,22],"have":[8],"enabled":[9],"highly":[10],"realistic":[11],"and":[12,23,50,57,77,83,101,173,177,192],"freely":[13],"renderable":[14],"digital":[15],"heads":[16],"from":[17,80],"a":[18,116,120],"single":[19],"portrait.":[20],"However,":[21],"rendering":[24],"can":[25],"weaken":[26],"the":[27,31,35,66,129,134,153,170,189,200],"forgery":[28],"traces":[29],"source":[32],"portrait,":[33],"making":[34],"resulting":[36],"face":[38,45,58],"difficult":[39],"to":[40,54,132],"classify":[41],"whether":[42],"its":[43],"underlying":[44],"is":[46],"real":[47,75],"or":[48],"fake,":[49],"thereby":[51],"posing":[52],"risks":[53],"identity":[55],"authentication":[56],"privacy.":[59],"To":[60,108],"study":[61],"this":[62,71,89],"problem,":[63],"we":[64,114],"introduce":[65],"first":[67,194],"large-scale":[68],"benchmark":[69],"for":[70,97,139,181],"task":[72],"by":[73],"collecting":[74],"portraits":[76,79],"fake":[78],"multiple":[81],"sources":[82],"evaluate":[84],"representative":[85],"existing":[86],"detectors":[87],"on":[88],"benchmark,":[90],"revealing":[91],"their":[92],"lack":[93],"of":[94,152],"explicit":[95],"mechanisms":[96],"retaining":[98],"fine-grained":[99,135],"information":[100,137],"maintaining":[102],"feature":[103,147],"consistency":[104,148],"across":[105,149,195],"rendered":[106,150],"views.":[107],"directly":[109],"address":[110],"these":[111],"two":[112],"limitations,":[113],"propose":[115],"detector":[117],"trained":[118],"with":[119],"two-stage":[121],"strategy.":[122],"In":[123],"Stage":[124,167],"I,":[125],"masked":[126],"autoencoding":[127],"encourages":[128],"visual":[130],"backbone":[131,172],"retain":[133],"appearance":[136],"required":[138],"local":[140],"reconstruction,":[141],"while":[142],"multi-view":[143],"contrastive":[144],"learning":[145],"enforces":[146],"views":[151],"same":[154],"head.":[155],"Since":[156],"CLS":[157,179],"tokens":[158,180],"at":[159],"different":[160],"depths":[161],"exhibit":[162],"complementary":[163],"spatial":[164],"attention":[165],"patterns,":[166],"II":[168],"freezes":[169],"adapted":[171],"concatenates":[174],"low-,":[175],"middle-,":[176],"high-level":[178],"classification.":[182],"Experiments":[183],"show":[184],"that":[185],"our":[186],"method":[187],"achieves":[188],"highest":[190],"accuracy":[191],"ranks":[193],"all":[196],"reported":[197],"metrics":[198],"among":[199],"evaluated":[201],"detectors.":[202]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}