{"id":"W2924203149","doi":"10.1002/cta.2623","title":"Using deep learning to combine static and dynamic power analyses of cryptographic circuits","year":2019,"lang":"en","type":"article","venue":"International Journal of Circuit Theory and Applications","topic":"Cryptographic Implementations and Security","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Side channel attack; Leakage (economics); Computer science; Cryptography; Dynamic demand; Power analysis; Computer engineering; Electronic circuit; Leakage power; Electronic engineering; Embedded system; Artificial neural network; Power (physics); Algorithm; Artificial intelligence; Engineering; Transistor; Electrical engineering","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":[0.0003995931,0.0004852481,0.0002382994,0.0006293003,0.0001734178,0.0004781919,0.000541837,0.0002908081,0.001198746],"category_scores_gemma":[0.00115784,0.0002507769,0.0003230476,0.0003549693,0.0003734299,0.0009377978,0.0004156082,0.0005131532,0.0001628079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007469089,"about_ca_system_score_gemma":0.0004925759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001450054,"about_ca_topic_score_gemma":0.002666807,"domain_scores_codex":[0.999798,0.00004427366,0.00001205098,0.00003195747,0.00008584736,0.00002788007],"domain_scores_gemma":[0.9995486,0.0001774112,0.00007287344,0.00007539133,0.0001097436,0.00001590809],"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":[0.0001558558,0.0001361711,0.003750512,0.00007968037,0.00009504767,0.0001066951,0.00005069219,0.7143893,0.05940425,0.009825161,0.0007538344,0.2112528],"study_design_scores_gemma":[0.000002513356,0.00002320123,0.000230839,0.000002165456,0.000005520023,0.00001508151,0.000002738566,0.9883795,0.009107184,0.002034234,0.0001942215,0.000002806366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3016538,0.0002851245,0.6913992,0.0003147124,0.0000397156,0.00004152402,0.00007141633,0.001439834,0.004754643],"genre_scores_gemma":[0.9476935,0.00005203773,0.05089672,0.00004740309,0.000008302146,0.00001668776,0.00004154519,0.00003282126,0.001211133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001450054,"threshold_uncertainty_score":0.005419195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02598280464344821,"score_gpt":0.3501942168546823,"score_spread":0.3242114122112341,"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."}}