{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00132227,0.001040139,0.0007415737,0.0003330371,0.0002998844,0.0005362562,0.0009476592,0.0008606715,0.001770742],"category_scores_gemma":[0.003739388,0.0002442379,0.0005242442,0.000297821,0.0007960825,0.001121011,0.001198774,0.002578406,0.0004620133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006007027,"about_ca_system_score_gemma":0.0004066184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005600933,"about_ca_topic_score_gemma":0.0007996247,"domain_scores_codex":[0.9992607,0.0002764752,0.00002698825,0.0001011744,0.000245043,0.0000895102],"domain_scores_gemma":[0.9987142,0.0007447962,0.000128842,0.0002354216,0.0001300811,0.00004658576],"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":[0.0002270379,0.00009512541,0.001316053,0.00009142976,0.0001020142,0.000145266,0.00006248218,0.8141741,0.01854966,0.03700849,0.003530772,0.1246976],"study_design_scores_gemma":[0.000003563374,0.00003724758,0.00009131843,0.000004856288,0.000005426755,0.00004433197,0.000002649856,0.9931392,0.003123016,0.002920481,0.0006241419,0.000003766194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0181035,0.0003320262,0.9770076,0.0003672812,0.00008934677,0.00006009475,0.00003751349,0.0004981219,0.00350456],"genre_scores_gemma":[0.8658429,0.0003195854,0.1289384,0.0004379594,0.00008793778,0.0001017148,0.0001059009,0.00009989472,0.004065654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001770742,"threshold_uncertainty_score":0.006992936,"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."}}