{"id":"W4288088872","doi":"10.48550/arxiv.1910.12084","title":"Detection of Adversarial Attacks and Characterization of Adversarial\\n Subspace","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Adversarial system; Subspace topology; Linear subspace; Computer science; Detector; Spectrogram; Artificial intelligence; Relation (database); Pattern recognition (psychology); Algorithm; Mathematics; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002165655,0.0007194836,0.0008201813,0.001010644,0.0004698621,0.001108051,0.0009673089,0.001151115,0.0008874489],"category_scores_gemma":[0.01262686,0.0002926613,0.0006396241,0.0004841473,0.00197309,0.002207663,0.002398908,0.002096119,0.0004056506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005967959,"about_ca_system_score_gemma":0.0006788662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008269784,"about_ca_topic_score_gemma":0.0006726002,"domain_scores_codex":[0.9978628,0.0007109547,0.00009728563,0.000448426,0.0006990824,0.0001815018],"domain_scores_gemma":[0.993611,0.003250806,0.000841092,0.00142586,0.0005845414,0.0002866347],"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":[0.0003542989,0.0001948387,0.01736411,0.000145448,0.0001594052,0.0003571465,0.0002857996,0.6621447,0.03203591,0.06964529,0.003322378,0.2139907],"study_design_scores_gemma":[0.00000220971,0.00004665844,0.0008500091,0.000008633315,0.000004181652,0.0001155382,0.00003051269,0.981719,0.005061674,0.01152561,0.0006252521,0.00001077696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09293148,0.0002994412,0.90347,0.0004515584,0.00005403721,0.00005370733,0.0001077416,0.0006720075,0.001960055],"genre_scores_gemma":[0.9128321,0.0002467146,0.08443598,0.0001838926,0.00006371694,0.00005956849,0.0003538605,0.00007619697,0.001747859],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002165655,"threshold_uncertainty_score":0.01145327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03546069160915891,"score_gpt":0.1812881476499253,"score_spread":0.1458274560407664,"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."}}