{"id":"W4324125491","doi":"10.1109/tnnls.2023.3252175","title":"Adversarial Danger Identification on Temporally Dynamic Graphs","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Foundation for Innovation","keywords":"Computer science; Adversarial system; Artificial intelligence; Multivariate statistics; Identification (biology); Machine learning; Generalization; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000779278,0.0002611113,0.0002637939,0.0003739564,0.0009312195,0.0003992398,0.0004222778,0.0001653057,0.000005415669],"category_scores_gemma":[0.00002288281,0.0002478877,0.0001187252,0.001008532,0.00006048249,0.0004273574,0.000008276802,0.001138926,0.00006037044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005381578,"about_ca_system_score_gemma":0.00001712298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009131841,"about_ca_topic_score_gemma":0.000009795622,"domain_scores_codex":[0.9975613,0.0005802832,0.0003954968,0.0006494379,0.0004001221,0.0004134128],"domain_scores_gemma":[0.9987345,0.0004522462,0.0002124568,0.0004214048,0.00005698369,0.0001224178],"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":[0.00003303379,0.00002102913,0.00006715081,0.00001763689,0.00002857044,0.00002065474,0.0002570391,0.9700911,0.0001239499,0.0005554729,0.0001283101,0.02865605],"study_design_scores_gemma":[0.0004107388,0.0001930298,0.0008956253,0.00006751098,0.00001701501,0.00001993435,0.0001205013,0.9972998,0.000008684588,0.00003148095,0.0006852036,0.0002504922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04857088,0.0000574362,0.9444671,0.000419131,0.005114133,0.0003206994,0.000001998729,0.0009445522,0.0001040954],"genre_scores_gemma":[0.9975895,0.0000547602,0.0001601183,0.00006577621,0.0001578417,0.00005388756,0.000009851778,0.00003709815,0.00187119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9490186,"threshold_uncertainty_score":0.9999973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01214025023442221,"score_gpt":0.2493797509602252,"score_spread":0.237239500725803,"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."}}