{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005143451,0.0002334682,0.0002063327,0.0002341839,0.0003018316,0.0005741373,0.0009162618,0.0001099852,0.0001286509],"category_scores_gemma":[0.0003419155,0.0002113104,0.0001044187,0.0007605472,0.00006758057,0.0009855445,0.0004775039,0.0003957583,0.0005527829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001341603,"about_ca_system_score_gemma":0.0001938347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002809793,"about_ca_topic_score_gemma":0.000002539768,"domain_scores_codex":[0.9980422,0.0001321223,0.0002866088,0.0006766338,0.0003576363,0.0005047958],"domain_scores_gemma":[0.9987324,0.0005035012,0.00004654259,0.0005128343,0.00007296624,0.0001317497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003305896,0.00006675397,0.000288436,0.0001458302,0.0001592109,0.001394886,0.002080085,0.08089381,0.007737765,0.8214704,0.01716838,0.06856138],"study_design_scores_gemma":[0.0003462475,0.00006275546,0.00004300632,0.00009468576,0.00002289107,0.00003625568,0.0001295586,0.9557373,0.002689583,0.006051559,0.03431881,0.0004673834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000929353,0.0002700878,0.9616189,0.001049107,0.001767115,0.0001469763,8.356827e-7,0.001831662,0.03238595],"genre_scores_gemma":[0.761118,0.0000116106,0.2360598,0.0003191914,0.0003496487,0.00001563889,0.000006027298,0.00002990096,0.002090152],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8748435,"threshold_uncertainty_score":0.8616987,"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."}}