{"id":"W2407561938","doi":"10.1109/lsp.2015.2438008","title":"Median Filtering Forensics Based on Convolutional Neural Networks","year":2015,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; National Science Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pooling; Image (mathematics); Pattern recognition (psychology); Filter (signal processing); Median filter; Residual; Computer vision; Image processing; Algorithm","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":[0.0002834266,0.0002164049,0.0001717878,0.0001607201,0.0001212804,0.0003942377,0.0004980103,0.0000698335,0.000002434219],"category_scores_gemma":[0.00004628791,0.0002077303,0.00006734312,0.00042193,0.000163224,0.0008974693,0.00005210405,0.0002718543,0.00002278698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509649,"about_ca_system_score_gemma":0.0001212077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007152374,"about_ca_topic_score_gemma":0.000003009493,"domain_scores_codex":[0.9981369,0.00004813803,0.0002414537,0.0004335734,0.0006871921,0.0004527598],"domain_scores_gemma":[0.9991267,0.0001062456,0.0001293879,0.0002565988,0.0001083302,0.0002727446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005304758,0.00004557649,0.0001161037,0.00002553958,0.000009576118,0.0001138468,0.0002603242,0.6151883,0.00189633,0.0001364069,0.00961211,0.3725428],"study_design_scores_gemma":[0.0004537779,0.0001439909,0.00009758949,0.00006853505,0.000004818299,0.00002957104,0.000007933323,0.9958655,0.002108494,0.0006269502,0.0003485985,0.0002442499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01870868,0.00002045818,0.9741956,0.003921425,0.002147004,0.0001142091,0.000001666406,0.0003332217,0.0005577479],"genre_scores_gemma":[0.9772369,8.350712e-8,0.01389269,0.008185061,0.0006271563,0.0000167621,0.000007199541,0.00002214122,0.00001205827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9603029,"threshold_uncertainty_score":0.8470995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02658748460942762,"score_gpt":0.2257852914226731,"score_spread":0.1991978068132455,"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."}}