{"id":"W3217267762","doi":"10.1109/access.2021.3129851","title":"FakeSafe: Human Level Steganography Techniques by Disinformation Mapping Using Cycle-Consistent Adversarial Network","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Steganography; Steganalysis; Computer science; Cover (algebra); Steganography tools; Payload (computing); Artificial intelligence; Information hiding; Distortion (music); Deep learning; Construct (python library); Benchmark (surveying); Data mining; Image (mathematics); Computer security; Computer network","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":[0.0008294987,0.0007267586,0.0004925099,0.0004831819,0.0003628133,0.0005512318,0.0008032431,0.0008744019,0.001372397],"category_scores_gemma":[0.002653327,0.0002529773,0.0005112294,0.000264013,0.001303779,0.001711353,0.001647142,0.001129858,0.0002911057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005743847,"about_ca_system_score_gemma":0.0005019325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008101803,"about_ca_topic_score_gemma":0.0007890016,"domain_scores_codex":[0.9994624,0.0001834321,0.00001849327,0.0001091051,0.000160263,0.00006632219],"domain_scores_gemma":[0.9988091,0.0005202373,0.0001827982,0.0003294384,0.0001017005,0.00005681139],"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":[0.0003220137,0.0001130132,0.0018233,0.0001503719,0.0001033931,0.0003196571,0.0002432128,0.7081459,0.04608242,0.09116095,0.002728323,0.1488074],"study_design_scores_gemma":[0.00000830199,0.0000646716,0.0001927086,0.00001129634,0.000009196515,0.0001269319,0.00001415046,0.976408,0.008147891,0.01370285,0.001300843,0.00001329847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05022776,0.0003343826,0.9451487,0.0003673646,0.0000553704,0.00006140183,0.00005218486,0.0004446424,0.00330813],"genre_scores_gemma":[0.9096863,0.0003422221,0.0857775,0.0001576553,0.00003074153,0.00006034924,0.00008399543,0.00005811639,0.003803189],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001372397,"threshold_uncertainty_score":0.004591107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05759893865491477,"score_gpt":0.3085817321137436,"score_spread":0.2509827934588288,"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."}}