{"id":"W2062233254","doi":"10.1109/icip.2011.6115853","title":"Modeling the EXIF-Image correlation for image manipulation detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Noise (video); Image (mathematics); Computer vision; Feature selection; Feature detection (computer vision); Correlation; Image file formats; Header; Statistical model; Image editing; Feature extraction; Image processing; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002756726,0.00009585135,0.00006765971,0.00007971846,0.0001554917,0.0001616277,0.0002567781,0.00004959853,0.000009327079],"category_scores_gemma":[0.0001011871,0.00007036699,0.00006290698,0.0002101584,0.00002657373,0.001822678,0.0000623617,0.00007064556,0.00008246356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000467986,"about_ca_system_score_gemma":0.00001272601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007681532,"about_ca_topic_score_gemma":0.00007823059,"domain_scores_codex":[0.9991978,0.00002226717,0.000195603,0.0002441875,0.000170578,0.0001695973],"domain_scores_gemma":[0.9993666,0.00005204194,0.00006013811,0.0003337096,0.0001507138,0.00003684233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009661208,0.0001044586,0.00003988686,0.00003152198,0.00003282928,0.000003328996,0.003374565,0.008355254,0.01454803,0.112754,0.0002739069,0.8603856],"study_design_scores_gemma":[0.000167447,0.0000794243,0.0002211556,0.000004274606,0.000006512433,0.00001315689,0.00006107884,0.9468815,0.01668419,0.03572556,0.00006346938,0.00009220812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01396219,0.000004199568,0.9691697,0.00008149051,0.001126025,0.0004078213,4.664049e-7,0.000301778,0.01494632],"genre_scores_gemma":[0.8750044,7.852307e-7,0.1245722,0.00006013858,0.00007390211,0.00005802569,0.000002410432,0.000009916438,0.0002182242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9385263,"threshold_uncertainty_score":0.2869483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04354613269985617,"score_gpt":0.2332412253540317,"score_spread":0.1896950926541755,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}