{"id":"W4283810295","doi":"10.1609/aaai.v36i2.20010","title":"Adversarial Attack for Asynchronous Event-Based Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Adversarial system; Asynchronous communication; Computer science; Artificial intelligence; Event (particle physics); Robustness (evolution); Machine learning; Set (abstract data type); Deep learning; Deep neural networks; Data mining","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":[0.0009144592,0.0001395662,0.0001610517,0.00008921071,0.000635644,0.00009602371,0.003765172,0.00003118511,0.0004722892],"category_scores_gemma":[0.0002206057,0.0001455605,0.00007070574,0.0003187066,0.00002740529,0.0005143831,0.002926792,0.0002544565,0.00002676456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001369181,"about_ca_system_score_gemma":0.0003495474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005749156,"about_ca_topic_score_gemma":0.00001329145,"domain_scores_codex":[0.9981652,0.000163591,0.0002277621,0.0006804669,0.0004180593,0.0003448722],"domain_scores_gemma":[0.9977894,0.000348232,0.0001173979,0.001633475,0.00003915363,0.00007232465],"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":[0.0000567556,0.0001062671,0.0002545255,0.0000125396,0.00002584518,0.0000137214,0.0001109964,0.9255338,0.00005270589,0.02807355,0.024164,0.02159523],"study_design_scores_gemma":[0.00111941,0.0001425071,0.00005151435,0.000001525687,0.000009272038,0.000005112676,0.0000399089,0.88508,0.00003761296,0.000328432,0.1130049,0.0001797821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003948174,0.00002353974,0.9935587,0.002354286,0.001748372,0.0003640366,0.0000421348,0.0003073812,0.001206721],"genre_scores_gemma":[0.6324967,2.780897e-7,0.3650057,0.001198424,0.0003164088,0.00008688495,0.0002040374,0.0000229554,0.0006685644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6321019,"threshold_uncertainty_score":0.6996689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05597670562048369,"score_gpt":0.3306019063794989,"score_spread":0.2746252007590153,"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."}}