{"id":"W4409370123","doi":"10.1609/aaai.v39i3.32263","title":"AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"HORIZON EUROPE Framework Programme","keywords":"Adversarial system; Computer science; Computer security; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001423588,0.0003208833,0.0003871837,0.0002666997,0.0005437772,0.0003230174,0.003045949,0.0001430361,0.00004125227],"category_scores_gemma":[0.003114226,0.0002618153,0.0002500907,0.001029362,0.000310994,0.0004254475,0.0005643677,0.0004169737,0.00001837317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001154981,"about_ca_system_score_gemma":0.000380722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005117532,"about_ca_topic_score_gemma":0.00001277186,"domain_scores_codex":[0.9972783,0.00005168036,0.0007528848,0.0007857505,0.0006065788,0.0005247756],"domain_scores_gemma":[0.9971045,0.0007046979,0.0005697691,0.0004834216,0.001058398,0.00007916292],"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":[0.0001630083,0.0001018321,0.0003938652,0.0000940715,0.00002729321,1.741198e-7,0.0005078274,0.006723976,0.01199548,0.8875861,0.0002388875,0.09216748],"study_design_scores_gemma":[0.0001432492,0.0002719794,0.0001642682,0.0003802473,0.00003889777,6.618257e-7,0.0003387567,0.6914078,0.1512585,0.1554024,0.0003268972,0.0002663053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05077165,0.00002422332,0.9326677,0.005989108,0.00198799,0.001174979,0.000008061965,0.000200024,0.007176301],"genre_scores_gemma":[0.9453049,0.000003355882,0.05376488,0.0003882506,0.0001241218,0.00009777684,0.000001520953,0.00001606379,0.0002991748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8945332,"threshold_uncertainty_score":0.9999834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216905457698699,"score_gpt":0.373906943296021,"score_spread":0.2522163975261511,"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."}}