{"id":"W4407130548","doi":"10.1109/dsc63484.2024.00061","title":"INN-based Robust JPEG Steganography Through Cover Coefficient Selection","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Steganography; Cover (algebra); Computer science; Selection (genetic algorithm); Steganalysis; JPEG; Transform coding; Artificial intelligence; Discrete cosine transform; Data compression; Engineering; Embedding","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003459802,0.0004357703,0.0004219454,0.0003892198,0.000165184,0.0002197071,0.0004584593,0.0002791486,0.0008460996],"category_scores_gemma":[0.0008214861,0.0001713807,0.0002517629,0.0002407048,0.0003112543,0.0005078861,0.0004863952,0.0003169632,0.0002895606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002376471,"about_ca_system_score_gemma":0.0002966631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001307377,"about_ca_topic_score_gemma":0.002772506,"domain_scores_codex":[0.9997608,0.00003488647,0.00001133052,0.0000453631,0.0001117725,0.00003587935],"domain_scores_gemma":[0.9997113,0.00008801075,0.00005136026,0.00005661662,0.00007541539,0.00001723827],"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":[0.0003702207,0.0001177602,0.002862595,0.000146457,0.00008332574,0.0003035761,0.0001179972,0.1464735,0.2418857,0.003685667,0.001989961,0.6019632],"study_design_scores_gemma":[0.00001518575,0.00008393981,0.00127575,0.000008256089,0.00002622554,0.0002919325,0.00002349307,0.9054239,0.09026662,0.001079306,0.001491086,0.00001428054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1326177,0.0004095325,0.8624371,0.00009387341,0.00003828545,0.00006107387,0.00006601003,0.001227557,0.0030489],"genre_scores_gemma":[0.7633133,0.0003326363,0.2310843,0.00009557917,0.00004335139,0.00004357805,0.0002949486,0.00009574603,0.004696669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001307377,"threshold_uncertainty_score":0.002830446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806915835450115,"score_gpt":0.2557484994472764,"score_spread":0.2376793410927752,"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."}}