{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002140358,0.001471855,0.002067449,0.001609814,0.000649342,0.0009883826,0.002116157,0.002037709,0.00151993],"category_scores_gemma":[0.005818602,0.0005990744,0.001341898,0.0007739895,0.002045421,0.002627417,0.003183998,0.002499881,0.000660904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009753355,"about_ca_system_score_gemma":0.0013995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001608168,"about_ca_topic_score_gemma":0.001695649,"domain_scores_codex":[0.9978542,0.0003187553,0.0001125162,0.0007543092,0.0006744944,0.0002857206],"domain_scores_gemma":[0.9978362,0.0005423958,0.0003077399,0.0007199831,0.0004512884,0.0001424701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003945187,0.0002741578,0.005241946,0.0002771787,0.0003136392,0.0005995684,0.0002456895,0.1624723,0.04303506,0.04011194,0.0131056,0.7339284],"study_design_scores_gemma":[0.00001464486,0.00006585749,0.000685211,0.00002057823,0.00003542423,0.0005959139,0.00001651671,0.9663335,0.02201713,0.008173041,0.00200629,0.00003582933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0127322,0.0003118275,0.9841151,0.0002234027,0.00008578946,0.00008223043,0.000065962,0.001470438,0.0009131366],"genre_scores_gemma":[0.5540267,0.0005273346,0.4392686,0.0006509027,0.0001917326,0.0002046835,0.0004205944,0.0002128424,0.004496546],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002140358,"threshold_uncertainty_score":0.01131946,"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."}}