{"id":"W4401326099","doi":"10.1109/tccn.2024.3438379","title":"Generative AI for Secure Physical Layer Communications: A Survey","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Wireless Communication Security Techniques","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Physical layer; Computer network; Layer (electronics); Telecommunications; Wireless","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"],"consensus_categories":[],"category_scores_codex":[0.0004462222,0.0002747919,0.0002758057,0.0002281985,0.0007448648,0.000251817,0.0007781258,0.0001356974,0.000008514402],"category_scores_gemma":[0.000008884428,0.0002972299,0.0001362448,0.0005856765,0.0003487334,0.0002968301,0.00002939565,0.0008719217,0.00001642731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008615047,"about_ca_system_score_gemma":0.00004306966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003090939,"about_ca_topic_score_gemma":0.0005574545,"domain_scores_codex":[0.9986531,0.0003558742,0.0003289974,0.0002733171,0.0001253652,0.0002633128],"domain_scores_gemma":[0.9948247,0.003299702,0.00003737091,0.001477411,0.0002736155,0.00008720253],"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":[0.00007424707,0.0005957415,0.00005127025,0.0002527949,0.0009222637,0.000001362197,0.006279788,0.00122584,0.002160812,0.009195071,0.002731621,0.9765092],"study_design_scores_gemma":[0.0003149865,0.0001038209,0.00004551152,0.0007197982,0.0001356935,0.000008646195,0.0002257541,0.9500621,0.003482101,0.002360596,0.04209996,0.0004410149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003217835,0.01687634,0.9741393,0.001202073,0.0002845935,0.0009195118,0.0005892002,0.001205702,0.00156543],"genre_scores_gemma":[0.9600771,0.03215238,0.005753534,0.0003107296,0.00008654472,0.001283954,0.0002004141,0.0000875769,0.00004777172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9760682,"threshold_uncertainty_score":0.999948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08242531335143641,"score_gpt":0.3473854756081475,"score_spread":0.264960162256711,"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."}}