{"id":"W4225322540","doi":"10.3390/s22093445","title":"A Universal Detection Method for Adversarial Examples and Fake Images","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Adversarial system; Computer science; Artificial intelligence; Computer vision; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005486223,0.0001113544,0.0001338471,0.0001304272,0.0005885899,0.00006228329,0.000323832,0.00003234303,0.00002024071],"category_scores_gemma":[0.0001777843,0.0001234621,0.00005710178,0.0002420993,0.00003379089,0.0002005344,0.0004582717,0.0002153725,0.000001584687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008107076,"about_ca_system_score_gemma":0.00003613222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002175048,"about_ca_topic_score_gemma":0.00001594311,"domain_scores_codex":[0.9987813,0.0002950203,0.0001186353,0.0003855426,0.0001988007,0.000220737],"domain_scores_gemma":[0.9991525,0.0004436873,0.00008806045,0.0002282175,0.00003515163,0.0000523774],"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":[0.000305609,0.00005774138,0.0003246123,0.0000398425,0.0001044493,0.00005948465,0.005612304,0.4854328,0.01834019,0.04436901,0.0005848361,0.4447691],"study_design_scores_gemma":[0.00117035,0.0002243214,0.0004920352,0.000002860241,0.00002479972,0.00006440823,0.001182292,0.9496147,0.002413265,0.003114723,0.04144195,0.000254281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03201077,0.00002557419,0.966019,0.0004403622,0.0007877764,0.0002146611,0.000009626605,0.0001813985,0.0003108332],"genre_scores_gemma":[0.5618359,0.0000031093,0.4373033,0.0001011961,0.0001909641,0.00002362379,0.00000384876,0.00001809018,0.0005198822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5298252,"threshold_uncertainty_score":0.5034637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01314637095750225,"score_gpt":0.2676303055536461,"score_spread":0.2544839345961438,"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."}}