{"id":"W4390116303","doi":"10.1016/j.cose.2023.103674","title":"Improving adversarial transferability through hybrid augmentation","year":2023,"lang":"en","type":"article","venue":"Computers & Security","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Basic and Applied Basic Research Foundation of Guangdong Province; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Transferability; Computer science; Adversarial system; Domain (mathematical analysis); Focus (optics); Masking (illustration); Artificial intelligence; Diversity (politics); Scaling; Frequency domain; Image (mathematics); Machine learning; Pattern recognition (psychology); Algorithm; Computer vision; Mathematics","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":[0.001926009,0.001504944,0.001037968,0.0006598231,0.0004355492,0.00111081,0.001664246,0.001489242,0.00456261],"category_scores_gemma":[0.008178939,0.0005061619,0.0009182955,0.0005099142,0.001696032,0.002975021,0.003770105,0.002663745,0.001095804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005331549,"about_ca_system_score_gemma":0.0006003003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001043497,"about_ca_topic_score_gemma":0.001031277,"domain_scores_codex":[0.9989241,0.0003512136,0.00004680058,0.0002375542,0.0003199069,0.0001205306],"domain_scores_gemma":[0.9964589,0.002116443,0.0002007465,0.0008275667,0.0003066392,0.00008973746],"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":[0.0002668261,0.0001341491,0.0006591966,0.0001144383,0.00008699531,0.0001422975,0.0000865407,0.8109971,0.01719342,0.0426602,0.003253032,0.1244059],"study_design_scores_gemma":[0.00000523384,0.00003552063,0.00008009234,0.000006714368,0.0000081662,0.00003329216,0.000004550267,0.9851659,0.002488928,0.01174907,0.0004156739,0.000006895951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01946295,0.0003032376,0.9736703,0.0003305152,0.0001036773,0.00004354036,0.00006230965,0.001354591,0.00466879],"genre_scores_gemma":[0.8755245,0.000289136,0.1160626,0.0003453084,0.0001628136,0.0001246963,0.0002445828,0.0002847991,0.006961631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00456261,"threshold_uncertainty_score":0.0152635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01467202256203794,"score_gpt":0.2663804536482066,"score_spread":0.2517084310861686,"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."}}