{"id":"W4409257386","doi":"10.1109/tmc.2025.3558793","title":"Plugging and Breathing on the Air: A Practical Defense System for Deep Learning-Based Wireless Semantic Communications","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China; National Research Foundation","keywords":"Computer science; Wireless; Artificial intelligence; Computer security; Multimedia; Telecommunications","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008314854,0.0001768592,0.0001985493,0.0001959211,0.002275186,0.0002292906,0.0004800073,0.00009812934,0.000001680342],"category_scores_gemma":[0.0000301794,0.0001522056,0.0001256907,0.0005310663,0.0000970308,0.0001629288,0.00001923902,0.0006889558,0.000007105282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001241921,"about_ca_system_score_gemma":0.00006891163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002763755,"about_ca_topic_score_gemma":0.00002909619,"domain_scores_codex":[0.9984329,0.0003978176,0.0003156301,0.0003980365,0.0001790303,0.00027658],"domain_scores_gemma":[0.9953195,0.003653763,0.0001300106,0.0007248998,0.0001145579,0.00005720382],"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":[0.00007870021,0.000298185,0.00001252562,0.0002224122,0.0000883336,0.00000580034,0.001513031,0.7348386,0.0003317591,0.02825732,0.00006217517,0.2342912],"study_design_scores_gemma":[0.0003803368,0.0001868151,0.00001229228,0.0004744203,0.00003715235,0.00003002628,0.0003853488,0.9943385,0.002921629,0.0001389362,0.0009533275,0.0001412797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02870526,0.00007607025,0.967406,0.001911306,0.0005670057,0.0006693398,0.000001428724,0.0004657765,0.0001978455],"genre_scores_gemma":[0.9899331,0.00001947367,0.009300109,0.0005226128,0.0000341382,0.0001505495,8.725558e-7,0.00001370653,0.00002545392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9612278,"threshold_uncertainty_score":0.9990237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01742850941955272,"score_gpt":0.2721124233355756,"score_spread":0.2546839139160229,"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."}}