{"id":"W4312438979","doi":"10.1109/tdsc.2022.3217569","title":"Cover Reproducible Steganography via Deep Generative Models","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Steganography; Computer science; Steganalysis; Cover (algebra); Theoretical computer science; Steganography tools; Decoding methods; Cryptography; Embedding; Artificial intelligence; Algorithm; Pattern recognition (psychology); Speech recognition","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000433175,0.0002432664,0.0002402225,0.0003756453,0.001705089,0.0001528791,0.0005366677,0.00005887391,0.00002233831],"category_scores_gemma":[0.000001103315,0.000248308,0.0001488502,0.0008746044,0.00005296856,0.0006445868,0.00003423553,0.0005672628,0.000002646273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004300183,"about_ca_system_score_gemma":0.00003059877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002727413,"about_ca_topic_score_gemma":0.000006690788,"domain_scores_codex":[0.9979401,0.0001876116,0.0002923693,0.000834187,0.0003489124,0.0003968136],"domain_scores_gemma":[0.998988,0.00009649378,0.0001144606,0.0006363549,0.00006544656,0.00009922977],"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":[0.00005345001,0.0002590305,0.00002476659,0.00002776316,0.0001017534,0.00006644863,0.003855535,0.8913401,0.001578335,0.005774674,0.0002483229,0.09666984],"study_design_scores_gemma":[0.0003798863,0.0003373959,0.000007641029,0.00001860762,0.00001900619,0.0001770209,0.0001048003,0.9436494,0.03088357,0.02228325,0.001727142,0.0004123117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01118715,0.0003417599,0.9862312,0.0001795524,0.0005240651,0.000265189,0.00001097437,0.0005387554,0.0007213184],"genre_scores_gemma":[0.9188277,0.00004692279,0.08050444,0.0004335405,0.00003488556,0.00003977169,0.000002720438,0.0000195032,0.00009057106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9076405,"threshold_uncertainty_score":0.9999969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01634097675994247,"score_gpt":0.2320379466060755,"score_spread":0.215696969846133,"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."}}