{"id":"W4226314137","doi":"10.1109/lcomm.2022.3167368","title":"Multi-Objective GAN-Based Adversarial Attack Technique for Modulation Classifiers","year":2022,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Wireless Signal Modulation Classification","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); Université du Québec à Montréal","funders":"Mitacs","keywords":"Adversarial system; Computer science; Jamming; Classifier (UML); Artificial intelligence; Machine learning; Generative grammar; Wireless; Generative adversarial network; Deep learning; Modulation (music); Adversarial machine learning; Task (project management); Telecommunications; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006646369,0.0001889258,0.0001772044,0.0003123926,0.001232079,0.00009828338,0.002671498,0.00006894609,0.00001528632],"category_scores_gemma":[0.00008401925,0.0002368896,0.0001515945,0.0008484035,0.0001551271,0.0004678424,0.0002336617,0.0003702492,0.00001393734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007552701,"about_ca_system_score_gemma":0.0001522786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004357093,"about_ca_topic_score_gemma":0.00002180039,"domain_scores_codex":[0.9978796,0.0005616787,0.0004193171,0.0004913218,0.0003724724,0.0002756146],"domain_scores_gemma":[0.9962053,0.0005811144,0.0003508258,0.002629888,0.0001589929,0.0000738435],"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":[0.00004314152,0.0003590382,0.0005594637,0.000012455,0.00003953416,8.598976e-7,0.0007128965,0.4996458,0.4834816,0.003793756,0.008568333,0.002783041],"study_design_scores_gemma":[0.0009309939,0.0000597893,0.002955844,0.00000769001,0.00001411799,0.000003481454,0.00005151709,0.9753088,0.008185241,0.0002481158,0.01193905,0.000295369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003229778,0.00001346954,0.9731387,0.02107942,0.0004717102,0.001533439,0.0000326345,0.0003001776,0.000200638],"genre_scores_gemma":[0.7430243,0.000001302325,0.2521628,0.001756748,0.00003819039,0.002821783,0.0001301907,0.00002426958,0.00004037256],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7397946,"threshold_uncertainty_score":0.9660078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0837073165904719,"score_gpt":0.3144816481457586,"score_spread":0.2307743315552867,"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."}}