{"id":"https://openalex.org/W7169869882","doi":"https://doi.org/10.48550/arxiv.2607.18230","title":"Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs","display_name":"Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs","publication_year":2026,"publication_date":"2026-07-20","ids":{"openalex":"https://openalex.org/W7169869882","doi":"https://doi.org/10.48550/arxiv.2607.18230"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.18230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.18230","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,"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.2607.18230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141305056","display_name":"Yi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125493198","display_name":"Xinyi Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Xinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141258526","display_name":"Jiacheng Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130409479","display_name":"Sondos Mahmoud Bsharat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bsharat, Sondos Mahmoud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141236754","display_name":"Jiacheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053213848","display_name":"X Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137899721","display_name":"Tran Dinh Tien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien, Tran Dinh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078458050","display_name":"Ahmed Elhagry","orcid":"https://orcid.org/0000-0002-8904-8240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elhagry, Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079065924","display_name":"Salwa K. Al Khatib","orcid":"https://orcid.org/0000-0002-9588-8473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khatib, Salwa K. Al","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141302465","display_name":"Tianjun Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Tianjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005913897","display_name":"Yonina C. Eldar","orcid":"https://orcid.org/0000-0003-4358-5304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eldar, Yonina C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079361172","display_name":"Jing\u2010Hao Xue","orcid":"https://orcid.org/0000-0003-1174-610X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Jing-Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141309881","display_name":"Hao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141257389","display_name":"Salman Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Salman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5141264129","display_name":"Zhiqiang Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Zhiqiang","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/T12357","display_name":"Digital Media Forensic Detection","score":0.9825000166893005,"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":0.9825000166893005,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.0044999998062849045,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.003599999938160181,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7124000191688538},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6725999712944031},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6172999739646912},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5321999788284302},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5151000022888184},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4885999858379364},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43470001220703125}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7124000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970000267028809},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6725999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302000284194946},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4885999858379364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4652999937534332},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.18230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.18230","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,"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.2607.18230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.18230","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"vision-language":[1],"models":[2,49],"(VLMs)":[3],"have":[4],"significantly":[5],"improved":[6],"image":[7,14,33],"generation":[8],"and":[9,23,84,100,134,172,195,202,212],"editing":[10],"capabilities,":[11],"making":[12],"pixel-level":[13,32,169],"tampering":[15,34,47,170],"detection":[16,35],"increasingly":[17],"important":[18],"yet":[19,62,164],"challenging":[20],"under":[21],"cross-model":[22],"out-of-distribution":[24],"shifts.":[25],"This":[26],"work":[27],"studies":[28],"domain":[29],"generalization":[30],"for":[31,167],"in":[36,87,199],"modern":[37,176],"VLMs":[38,207],"like":[39],"ChatGPT,":[40],"Gemini,":[41],"Qwen-Image,":[42],"etc.,":[43],"aiming":[44],"to":[45,137,154],"learn":[46],"localization":[48,171],"that":[50,80,105],"remain":[51],"robust":[52],"across":[53,175,205],"diverse":[54],"VLM-generated":[55],"manipulation":[56],"distributions.":[57],"We":[58],"propose":[59],"a":[60,75,117,138,162,190],"simple":[61,118,163],"effective":[63],"domain-generalized":[64],"training":[65,102],"framework":[66,183],"built":[67],"on":[68,127],"two":[69],"practical":[70],"strategies.":[71],"First,":[72],"we":[73,115],"introduce":[74],"balanced":[76],"minibatch":[77],"sampling":[78],"scheme":[79],"strategically":[81],"samples":[82],"tampered":[83],"real":[85],"images":[86],"each":[88,106],"minibatch,":[89],"preventing":[90],"biased":[91],"optimization":[92,107],"toward":[93],"either":[94],"manipulated":[95],"artifacts":[96],"or":[97],"clean-image":[98],"priors":[99],"avoiding":[101],"collapse,":[103],"ensuring":[104],"step":[108],"receives":[109],"proper":[110],"sampled":[111],"gradient":[112],"signals.":[113],"Second,":[114],"adopt":[116],"late-injection":[119],"strategy,":[120],"where":[121],"the":[122,179,185],"detector":[123],"is":[124,217],"first":[125],"trained":[126],"large-scale":[128],"base":[129],"data":[130,145],"until":[131],"stable":[132],"convergence,":[133],"then":[135],"exposed":[136],"small":[139],"amount":[140],"of":[141,193,208],"newly":[142],"selected":[143],"supporting":[144],"from":[146],"emerging":[147],"VLM":[148],"distributions,":[149],"improving":[150,168],"adaptability":[151],"without":[152],"overfitting":[153],"limited":[155],"new":[156],"domains.":[157],"Together,":[158],"these":[159],"components":[160],"provide":[161],"strong":[165],"recipe":[166],"OOD":[173,206],"robustness":[174],"VLMs.":[177],"Despite":[178],"conceptual":[180],"simplicity,":[181],"our":[182],"outperforms":[184],"prior":[186],"state-of-the-art":[187],"PIXAR":[188],"by":[189],"large":[191],"margin":[192],"26.1%":[194],"26.8%":[196],"relative":[197],"improvement":[198],"average":[200],"gIoU":[201],"cIoU,":[203],"respectively,":[204],"GPT-Images-2.0,":[209],"Gemini-3.1,":[210],"FLUX.2,":[211],"Seedream":[213],"4.5.":[214],"Our":[215],"code":[216],"available":[218],"at":[219],"https://github.com/VILA-Lab/PIXAR-DG":[220]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-22T00:00:00"}