{"id":"W4327919584","doi":"10.1016/j.micpro.2023.104800","title":"EAM: Ensemble of approximate multipliers for robust DNNs","year":2023,"lang":"en","type":"article","venue":"Microprocessors and Microsystems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Robustness (evolution); Deep neural networks; Transferability; Exploit; Adversarial system; Multiplier (economics); Range (aeronautics); Deep learning; Artificial intelligence; Computer engineering; Machine learning; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001975198,0.001626385,0.001374139,0.0009386427,0.0004180348,0.0009872674,0.002137079,0.001987316,0.005884365],"category_scores_gemma":[0.004583161,0.0008434698,0.0008633153,0.0008354919,0.0004460432,0.001802093,0.001930907,0.002569674,0.001969371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000645274,"about_ca_system_score_gemma":0.001188864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00247468,"about_ca_topic_score_gemma":0.005059614,"domain_scores_codex":[0.9993599,0.0001810489,0.00003706072,0.0001647153,0.0001927983,0.00006457177],"domain_scores_gemma":[0.9990644,0.0003840054,0.00007459731,0.000177413,0.0002501197,0.00004956889],"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":[0.0002414041,0.00006841461,0.0004202017,0.0001147078,0.000168463,0.00005880029,0.00003437643,0.5587046,0.0053743,0.008936076,0.006225103,0.4196535],"study_design_scores_gemma":[0.000008584534,0.00003450569,0.00005233819,0.000009414375,0.00001015186,0.00001865514,0.000003287468,0.9942356,0.001574866,0.002863559,0.001183762,0.000005272451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003785938,0.000390616,0.9936122,0.00007975062,0.00008078894,0.00003951041,0.0001129192,0.001229436,0.0006689127],"genre_scores_gemma":[0.1371484,0.0003955986,0.8549044,0.0002463553,0.0001502342,0.0002820978,0.0007732706,0.0004101465,0.005689461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005884365,"threshold_uncertainty_score":0.01968521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02134753520366136,"score_gpt":0.2552095641008111,"score_spread":0.2338620288971498,"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."}}