{"id":"W2618218947","doi":"10.18653/v1/p17-3017","title":"Generating Steganographic Text with LSTMs","year":2017,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Steganography; Encryption; Adversary; Word (group theory); Artificial intelligence; Artificial neural network; Term (time); Quality (philosophy); Natural language processing; Information retrieval; Computer security; Embedding; Linguistics","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":[0.000218987,0.0001032432,0.0001254927,0.00005736445,0.0005424058,0.001034129,0.001130357,0.00003088069,0.00004074282],"category_scores_gemma":[0.00001716996,0.00006708348,0.00006573896,0.00008038656,0.00005061253,0.0005102607,0.0001767064,0.00009837111,0.00004229913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006289799,"about_ca_system_score_gemma":0.00002175401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003862133,"about_ca_topic_score_gemma":0.0004042313,"domain_scores_codex":[0.9991299,0.00002009954,0.0001384016,0.0002923468,0.0002047978,0.0002144895],"domain_scores_gemma":[0.9992226,0.0000184795,0.0001290722,0.0004995657,0.00007179212,0.00005852082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002173683,0.00003416918,0.002499144,0.000005087873,0.00007831939,0.00003825438,0.0006877928,0.004130013,0.0001636287,0.9571349,0.0006677101,0.03455878],"study_design_scores_gemma":[0.0001377165,0.00004941466,0.0007935951,0.00001505713,0.000006889905,0.00001255319,0.00004378983,0.9978979,0.0002077298,0.00001231286,0.0006853814,0.000137719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1740448,0.00002636754,0.810903,0.0004289306,0.0001087067,0.00003739572,9.384279e-8,0.0001026152,0.01434815],"genre_scores_gemma":[0.9553681,0.000001807831,0.04264439,0.0002694283,0.00009314768,0.000002567201,4.08583e-7,0.000005403132,0.001614762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9937679,"threshold_uncertainty_score":0.9972131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143611603146207,"score_gpt":0.2337032714774246,"score_spread":0.2193421111628039,"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."}}