{"id":"W4366817438","doi":"10.1007/s40747-023-01060-0","title":"SGMA: a novel adversarial attack approach with improved transferability","year":2023,"lang":"en","type":"article","venue":"Complex & Intelligent Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Transferability; Adversarial system; Computer science; Transformation (genetics); Grid; Vulnerability (computing); Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Machine learning; Data mining; Computer security; 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":[0.001087483,0.00107933,0.001039301,0.0006872228,0.0003986426,0.0008309805,0.001476935,0.001275106,0.002578384],"category_scores_gemma":[0.003179919,0.0003428269,0.0009580946,0.000355559,0.001480701,0.001643683,0.002697502,0.002055163,0.0006361248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005458603,"about_ca_system_score_gemma":0.0006984746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001034033,"about_ca_topic_score_gemma":0.0007819739,"domain_scores_codex":[0.9989024,0.0003071719,0.00004968371,0.0001896176,0.0004168166,0.0001343749],"domain_scores_gemma":[0.9984605,0.0006505789,0.0001971373,0.0003986191,0.0001870113,0.0001061875],"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":[0.0003076222,0.0001309438,0.0008738514,0.00009407715,0.0001375509,0.0002656997,0.0001147475,0.7281454,0.03688275,0.03961705,0.004493247,0.1889371],"study_design_scores_gemma":[0.000005719355,0.00004235489,0.00006073235,0.000003279861,0.000006012875,0.00004512285,0.000003729444,0.9913468,0.002927947,0.004988541,0.0005639197,0.000005881636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02334752,0.0002549907,0.9722726,0.0002781722,0.00007378945,0.00006283266,0.00002734893,0.001393843,0.002288878],"genre_scores_gemma":[0.8494771,0.0002550863,0.1444738,0.0003891829,0.0001073561,0.0001235231,0.0001100404,0.0002031768,0.004860708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002578384,"threshold_uncertainty_score":0.008625507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08224180129885214,"score_gpt":0.2956072811599041,"score_spread":0.2133654798610519,"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."}}