{"id":"W4399531570","doi":"10.1109/csnt60213.2024.10546022","title":"Designing Explainable Defenses Against Sophisticated Adversarial Attacks","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Adversarial system; Computer science; Interpretability; Robustness (evolution); Reinforcement learning; Artificial intelligence; Adaptability; Transparency (behavior); Flexibility (engineering); Machine learning; Computer security","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":[0.001971194,0.001015691,0.0005052665,0.0005980651,0.0004036089,0.001259668,0.001494332,0.001235871,0.002899891],"category_scores_gemma":[0.006592319,0.0003896965,0.0007652154,0.00019946,0.001676453,0.002436653,0.002635109,0.002048237,0.0005774788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007487215,"about_ca_system_score_gemma":0.001014933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008341471,"about_ca_topic_score_gemma":0.001303397,"domain_scores_codex":[0.9989709,0.0003648717,0.00004321158,0.0001999719,0.0002834153,0.000137621],"domain_scores_gemma":[0.9968895,0.001605826,0.000437884,0.000730488,0.000221365,0.0001148512],"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":[0.0003090733,0.0001345201,0.005628593,0.0003574385,0.0002626379,0.0002820917,0.0005419989,0.7079603,0.03195065,0.09128448,0.00289923,0.158389],"study_design_scores_gemma":[0.0000174944,0.0001246249,0.0005776635,0.00003253745,0.00004671891,0.0001279237,0.00006453429,0.9480059,0.008032303,0.03935016,0.003597823,0.00002241149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05071265,0.0003301981,0.9420057,0.0006068076,0.00004245611,0.0000999441,0.00007147793,0.001922874,0.004207906],"genre_scores_gemma":[0.8493165,0.0003254965,0.1468497,0.0002756019,0.00003824509,0.0001238421,0.0001698679,0.0001993043,0.002701231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002899891,"threshold_uncertainty_score":0.01042485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0162113499643965,"score_gpt":0.2658037361363406,"score_spread":0.2495923861719441,"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."}}