{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005326367,0.002546158,0.001237729,0.001673297,0.0005904644,0.001597791,0.001977877,0.002122512,0.003451539],"category_scores_gemma":[0.01761011,0.0004773303,0.0008835067,0.0007287303,0.001708326,0.002958195,0.002200292,0.002533274,0.001154366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001466343,"about_ca_system_score_gemma":0.001310575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002395005,"about_ca_topic_score_gemma":0.003085453,"domain_scores_codex":[0.9959174,0.001596865,0.0002509803,0.0005806652,0.001296114,0.0003580226],"domain_scores_gemma":[0.991038,0.00536888,0.0005948836,0.001915196,0.0007657168,0.0003174425],"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":[0.0006878242,0.0003981823,0.004300515,0.0005923458,0.0003855126,0.0001183936,0.00006594702,0.8650635,0.007242655,0.01390755,0.0134994,0.09373812],"study_design_scores_gemma":[0.00005875839,0.0004435474,0.0006047791,0.00004087875,0.00003065127,0.0001087284,0.00002128357,0.986333,0.005833577,0.004389847,0.002111176,0.00002381373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3141421,0.007029902,0.6278802,0.001891276,0.001194755,0.001015353,0.00253068,0.01741877,0.02689713],"genre_scores_gemma":[0.7789901,0.001126049,0.2098341,0.000605205,0.0001375962,0.0004650313,0.003636361,0.001070916,0.004134655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005326367,"threshold_uncertainty_score":0.0281688,"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."}}