{"id":"W2040405999","doi":"10.1007/s10044-012-0303-9","title":"Efficient steganalysis of images: learning is good for anticipation","year":2012,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Steganalysis; Steganography; Artificial intelligence; Pattern recognition (psychology); Computer science; Anticipation (artificial intelligence); Embedding; Mathematics; Computer vision","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":[0.0002646552,0.0000844002,0.0001951515,0.0003122337,0.0001597114,0.00003802585,0.000196911,0.00002997583,0.000004594652],"category_scores_gemma":[0.000004938039,0.00007452547,0.0001904772,0.001061671,0.00003057359,0.00009466404,0.00006171945,0.00004643033,0.000001445212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006815119,"about_ca_system_score_gemma":0.000003338876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002677567,"about_ca_topic_score_gemma":0.000002748104,"domain_scores_codex":[0.9992564,0.00002922345,0.0002266629,0.0002104055,0.0001131831,0.0001641086],"domain_scores_gemma":[0.999289,0.00007431051,0.000179901,0.0003118597,0.00008955514,0.00005536272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002564595,0.0003216477,0.6756158,0.00007696573,0.0009107307,6.989274e-8,0.001658121,0.0023399,0.004229936,0.01173718,0.00003440973,0.3030727],"study_design_scores_gemma":[0.0004699223,0.0001082894,0.2210041,0.00003232442,0.003422602,0.000002067472,0.0002613279,0.6446123,0.1157972,0.003583988,0.009978482,0.0007274107],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02535333,0.0001520591,0.9740139,0.000105132,0.00000541981,0.0001651992,0.00001343932,0.00005861611,0.0001329599],"genre_scores_gemma":[0.9741265,0.0000317221,0.02552602,0.00005265151,0.00002475202,0.0001762595,0.00001929307,0.000004172638,0.0000386717],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9487731,"threshold_uncertainty_score":0.3039061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01475364422384242,"score_gpt":0.2871244033667694,"score_spread":0.272370759142927,"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."}}