{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004846046,0.0007331263,0.0005736582,0.0005724039,0.000227824,0.0004597264,0.0006438224,0.001003212,0.002240012],"category_scores_gemma":[0.003308099,0.0002544854,0.0004016663,0.0004315955,0.0004204129,0.001402301,0.0007154758,0.0009507689,0.001215573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004479113,"about_ca_system_score_gemma":0.0003415916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008716235,"about_ca_topic_score_gemma":0.001519954,"domain_scores_codex":[0.9997045,0.00006828296,0.00001795348,0.00008405583,0.0000749815,0.00005011306],"domain_scores_gemma":[0.9991848,0.0004600703,0.00007511611,0.0001014954,0.0001558275,0.00002265172],"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":[0.0007516541,0.0001979519,0.001560647,0.0003669031,0.00009058395,0.0004555687,0.000210555,0.2776195,0.1296707,0.01015359,0.006512563,0.5724097],"study_design_scores_gemma":[0.00001476916,0.00004969988,0.000236237,0.000009729682,0.000009573439,0.00006461607,0.00002077666,0.9634519,0.02973063,0.005468663,0.0009352296,0.000008182679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1548957,0.0005463648,0.8352123,0.0009015437,0.0002180774,0.00009892166,0.0006872978,0.003975486,0.003464354],"genre_scores_gemma":[0.8309589,0.0002829087,0.1612646,0.0002829815,0.0001156718,0.0001269557,0.001209593,0.0001694262,0.005588935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002240012,"threshold_uncertainty_score":0,"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."}}