{"id":"W2981692241","doi":"10.1109/icassp40776.2020.9052913","title":"Detection of Adversarial Attacks and Characterization of Adversarial Subspace","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Adversarial system; Subspace topology; Computer science; Linear subspace; Detector; Spectrogram; Artificial intelligence; Relation (database); Pattern recognition (psychology); Algorithm; Mathematics; Data mining; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003861123,0.0003324454,0.0006632282,0.0002315269,0.0000737037,0.00007018087,0.000893285,0.0004336231,0.00002568639],"category_scores_gemma":[0.0002929789,0.0003509055,0.0001609612,0.000358645,0.0001248466,0.0004349363,0.002530163,0.0007113154,0.000003838663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006382304,"about_ca_system_score_gemma":0.0002079661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002751348,"about_ca_topic_score_gemma":0.00001744609,"domain_scores_codex":[0.997573,0.0002449618,0.0006511626,0.0007948267,0.0005124704,0.0002235356],"domain_scores_gemma":[0.9978356,0.0001371833,0.001014009,0.0006779249,0.0002257754,0.000109466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001179888,0.0002010719,0.003211401,0.001802751,0.0005479532,0.00002500242,0.008645331,0.02937646,0.8616253,0.02678011,0.00005247832,0.06655229],"study_design_scores_gemma":[0.002462733,0.0003938417,0.02265083,0.0002706826,0.0001950197,0.00001124142,0.0001095014,0.8615409,0.1076596,0.003017402,0.0007688159,0.0009194319],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.111863,0.00001825128,0.8839923,0.0005556876,0.002401605,0.0004122558,0.00001598452,0.0001643669,0.0005765756],"genre_scores_gemma":[0.9735651,0.00004029858,0.025748,0.00004178704,0.0004560178,0.00000947672,0.00004357912,0.00002607269,0.00006964459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8617021,"threshold_uncertainty_score":0.9998943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164143466682037,"score_gpt":0.2532152622154554,"score_spread":0.2368009155472517,"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."}}