{"id":"W4401768877","doi":"10.18280/isi.290438","title":"Sensitivity of a Convolutional Neural Network for Different Pooling Layers in Spatial Domain Steganalysis","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pooling; Convolutional neural network; Steganalysis; Sensitivity (control systems); Computer science; Artificial intelligence; Domain (mathematical analysis); Pattern recognition (psychology); Steganography; Mathematics; Embedding; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00407505,0.00169884,0.0007683493,0.0009595623,0.0004824164,0.001138609,0.0008295379,0.001495463,0.00114522],"category_scores_gemma":[0.01675624,0.0005236002,0.0009425836,0.0004312184,0.0009241003,0.002325683,0.001327567,0.001579262,0.000331716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001395629,"about_ca_system_score_gemma":0.0007260107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006700292,"about_ca_topic_score_gemma":0.004430182,"domain_scores_codex":[0.9988614,0.0003160871,0.0001147334,0.0002629725,0.0002380741,0.0002067304],"domain_scores_gemma":[0.994994,0.00342235,0.0004671011,0.0004429002,0.0005454254,0.0001283408],"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":[0.001381537,0.0002488497,0.01189569,0.0004389651,0.0004907987,0.0004008863,0.0001543327,0.8259994,0.03765987,0.003319413,0.001366718,0.1166435],"study_design_scores_gemma":[0.00001931229,0.0004494884,0.004103375,0.0001034497,0.0001549235,0.0001785209,0.00005351296,0.960107,0.03177992,0.002529896,0.0004759138,0.00004468635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8360467,0.005964375,0.1474861,0.001624773,0.0004080682,0.0001657301,0.0003423947,0.001277359,0.006684629],"genre_scores_gemma":[0.9875185,0.0008887622,0.01027261,0.000171933,0.00002913336,0.00003250253,0.0001724884,0.00005480204,0.0008593567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006700292,"threshold_uncertainty_score":0.02155119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01169822431220541,"score_gpt":0.2376922625531167,"score_spread":0.2259940382409112,"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."}}