{"id":"https://openalex.org/W7131399153","doi":"https://doi.org/10.48550/arxiv.2602.18842","title":"Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification","display_name":"Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7131399153","doi":"https://doi.org/10.48550/arxiv.2602.18842"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.18842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18842","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.18842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126664423","display_name":"Jiangling Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jiangling","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126708754","display_name":"Shuxuan Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Shuxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126682393","display_name":"Bofan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bofan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126719784","display_name":"Siqiang Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Siqiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109747583","display_name":"Jirui Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jirui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123901368","display_name":"Yaxiong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yaxiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126793665","display_name":"Ziyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ziyu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5126664423"],"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9783999919891357,"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":0.9783999919891357,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.006899999920278788,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/inpainting","display_name":"Inpainting","score":0.6083999872207642},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5925999879837036},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5838000178337097},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5252000093460083},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4896000027656555},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.4399999976158142},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4138999879360199},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39590001106262207}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7906000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014999985694885},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6083999872207642},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C65185188","wikidata":"https://www.wikidata.org/wiki/Q107775","display_name":"Streak","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2879999876022339},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.27900001406669617},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.18842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18842","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.18842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18842","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.721851110458374,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,17,26,160],"highly":[3],"realistic":[4],"AI-generated":[5],"images":[6,84],"poses":[7],"critical":[8],"challenges":[9],"for":[10,112,143],"digital":[11],"forensics,":[12],"demanding":[13],"precise":[14,144],"pixel-level":[15],"localization":[16],"manipulated":[18],"regions.":[19],"Existing":[20],"methods":[21],"predominantly":[22],"learn":[23],"discriminative":[24],"patterns":[25],"specific":[27],"forgeries":[28],"and":[29,136,164],"often":[30],"struggle":[31],"with":[32,108],"novel":[33],"manipulations":[34,67],"as":[35,85],"editing":[36],"techniques":[37],"continue":[38],"to":[39,56,131,176],"evolve.":[40],"We":[41],"propose":[42],"the":[43,63,70,105,133,169],"Iterative":[44],"Forgery":[45],"Amplifier":[46],"Network":[47,102],"(IFA-Net),":[48],"which":[49],"shifts":[50],"from":[51,69],"learning":[52],"\"what":[53,58],"is":[54,59],"fake\"":[55],"modeling":[57],"real\".":[60],"Grounded":[61],"in":[62,140,162,166],"principle":[64],"that":[65,123,154],"all":[66],"deviate":[68],"natural":[71],"image":[72,107],"manifold,":[73],"IFA-Net":[74,155],"leverages":[75],"a":[76,86,94,117],"frozen":[77],"Masked":[78],"Autoencoder":[79],"(MAE)":[80],"pretrained":[81],"on":[82,148],"real":[83],"universal":[87],"realness":[88],"prior.":[89],"Our":[90],"framework":[91],"operates":[92],"through":[93],"two-stage":[95],"closed-loop":[96],"process:":[97],"an":[98,157],"initial":[99],"Dual-Stream":[100],"Segmentation":[101],"(DSSN)":[103],"fuses":[104],"original":[106],"MAE":[109,134],"reconstruction":[110,138],"residuals":[111],"coarse":[113,126],"localization,":[114],"followed":[115],"by":[116],"Task-Adaptive":[118],"Prior":[119],"Injection":[120],"(TAPI)":[121],"module":[122],"converts":[124],"this":[125],"prediction":[127],"into":[128],"guiding":[129],"prompts":[130],"steer":[132],"decoder":[135],"amplify":[137],"failures":[139],"suspicious":[141],"regions":[142],"refinement.":[145],"Extensive":[146],"experiments":[147],"four":[149],"diffusion-based":[150],"inpainting":[151],"benchmarks":[152],"show":[153],"achieves":[156],"average":[158],"improvement":[159],"6.5%":[161],"IoU":[163],"8.1%":[165],"F1-score":[167],"over":[168],"second-best":[170],"method,":[171],"while":[172],"demonstrating":[173],"strong":[174],"generalization":[175],"traditional":[177],"manipulation":[178],"types.":[179]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}