{"id":"W4410226734","doi":"10.1109/tnse.2025.3568824","title":"Concealing Radio Frequency Fingerprints via Active Adversarial Perturbation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Wireless Signal Modulation Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Adversarial system; Radio frequency; Perturbation (astronomy); Computer science; Physics; Control theory (sociology); Telecommunications; Artificial intelligence","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":[0.0004418607,0.0001232548,0.0001104979,0.0002668995,0.0004480997,0.0001567929,0.0003686096,0.00005922302,0.000003975756],"category_scores_gemma":[0.00002028579,0.0001307553,0.00003096403,0.001497077,0.00009145573,0.0009525124,0.000004746262,0.0001861679,0.000005030955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002217145,"about_ca_system_score_gemma":0.0001770392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302328,"about_ca_topic_score_gemma":0.00000268584,"domain_scores_codex":[0.9988074,0.00002166508,0.0001834364,0.0004040352,0.0003038788,0.0002795822],"domain_scores_gemma":[0.9993241,0.0001459886,0.00004494218,0.000266649,0.0001374412,0.0000808166],"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":[0.000004901587,0.00001666876,0.00001201566,0.000009034425,0.00001182965,8.269709e-7,0.0002719384,0.8778368,0.02336271,0.01484661,0.00001648253,0.08361013],"study_design_scores_gemma":[0.0001771967,0.0000224019,0.002132633,0.00006423877,0.000007463971,0.000002940893,0.00001046207,0.9854793,0.01092736,0.0009294798,0.0001109549,0.0001355585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01044133,0.00003151877,0.9866529,0.0004792386,0.001699793,0.0001460293,8.036516e-7,0.0001797768,0.0003686238],"genre_scores_gemma":[0.9837559,0.00001914871,0.01595751,0.0001063041,0.00007327129,0.00002583856,3.560307e-7,0.000005119597,0.0000565016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9733146,"threshold_uncertainty_score":0.5332046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008827533102215441,"score_gpt":0.2146336871572481,"score_spread":0.2058061540550327,"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."}}