{"id":"W4380607095","doi":"10.1109/tdsc.2023.3285590","title":"Multi-Modality Ensemble Distortion for Spatial Steganography With Dynamic Cost Correction","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Pixel; Distortion (music); Steganalysis; Steganography; Computer science; Artificial intelligence; Embedding; Algorithm; Pattern recognition (psychology); Computer vision; Telecommunications","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":[0.0002798789,0.0002150479,0.0002058201,0.0002858066,0.0008121988,0.0001409067,0.0002197857,0.0001024641,7.95337e-7],"category_scores_gemma":[0.000003072003,0.0001942924,0.0001131055,0.0006131188,0.00005545639,0.000387967,0.000006067351,0.0002456318,0.000002113125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004247325,"about_ca_system_score_gemma":0.00002730315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009031523,"about_ca_topic_score_gemma":0.0004364561,"domain_scores_codex":[0.998622,0.00006161142,0.0002364716,0.0005227852,0.0001860315,0.000371089],"domain_scores_gemma":[0.9992426,0.0001697841,0.0001102099,0.0002945345,0.00009545264,0.00008742703],"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":[0.0003217011,0.0003432753,0.0004665683,0.0001781758,0.0001415172,0.0000330991,0.002227253,0.09477913,0.004362123,0.0002797464,0.0001944083,0.896673],"study_design_scores_gemma":[0.0007678897,0.0003569254,0.0008389738,0.0001107613,0.00002640503,0.00004008102,0.00006028055,0.9753353,0.02087364,0.0006392521,0.0006300407,0.0003204682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02674526,0.00002563756,0.9705606,0.0001293783,0.0008992226,0.0005646336,0.00001705222,0.001036349,0.00002191984],"genre_scores_gemma":[0.9560291,0.0000422349,0.04368819,0.0000445669,0.00002407952,0.00006538803,0.00001344421,0.00002029544,0.00007269799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9292839,"threshold_uncertainty_score":0.7923015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01697473529321391,"score_gpt":0.2669819941858309,"score_spread":0.250007258892617,"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."}}