{"id":"W3119147336","doi":"10.1109/tcad.2021.3091436","title":"Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Detector; Computer science; MNIST database; Subnetwork; Artificial intelligence; Robustness (evolution); Artificial neural network; Adversarial system; Convolutional neural network; Deep learning; Inference; Computer engineering; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006956892,0.0003218724,0.0005123946,0.0004312358,0.0002172704,0.0001965107,0.0001867518,0.0002090902,0.000002045545],"category_scores_gemma":[0.00001646074,0.0003125655,0.00008867509,0.0009582114,0.00008852474,0.0002269531,0.000008308755,0.0005176052,5.489123e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256866,"about_ca_system_score_gemma":0.0001333173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006240153,"about_ca_topic_score_gemma":0.0000768465,"domain_scores_codex":[0.9968511,0.001234793,0.0005631919,0.000702384,0.000303978,0.0003445846],"domain_scores_gemma":[0.9981674,0.0008279675,0.0002015539,0.0004073959,0.0002567471,0.0001389375],"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":[0.00002954847,0.0001245138,0.0000196263,0.0000385213,0.00003395065,0.0001418317,0.0001385228,0.8888738,0.003265217,0.0001726528,0.000003410343,0.1071585],"study_design_scores_gemma":[0.0009707364,0.0002467115,0.0001311412,0.0002713286,0.0000229164,0.0002265266,0.00008846247,0.9923917,0.005353519,0.000008230545,0.000007953608,0.0002807839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01922932,0.0002792446,0.9784476,0.00004810666,0.001597707,0.0002384185,0.000005714779,0.000139301,0.00001455151],"genre_scores_gemma":[0.9937254,0.00002455822,0.006035467,0.00009449424,0.00005659512,0.00002114039,0.000003185987,0.0000236089,0.00001555165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744961,"threshold_uncertainty_score":0.9999326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01966606630537448,"score_gpt":0.214381650539811,"score_spread":0.1947155842344366,"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."}}