{"id":"W4387993744","doi":"10.1145/3623652.3623665","title":"DINAR: Enabling Distribution Agnostic Noise Injection in Machine Learning Hardware","year":2023,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Noise (video); Robustness (evolution); Gaussian noise; Embedded system; Artificial intelligence; Image (mathematics)","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":[0.001395509,0.001124394,0.0007359855,0.0006562089,0.0005827156,0.001445507,0.002742312,0.001053276,0.007135502],"category_scores_gemma":[0.006649524,0.0004302845,0.0005421708,0.0004264346,0.001205336,0.002559777,0.002823743,0.002399336,0.002095719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009073915,"about_ca_system_score_gemma":0.001164274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004878613,"about_ca_topic_score_gemma":0.001230966,"domain_scores_codex":[0.9978657,0.0003644851,0.0001332394,0.0004510143,0.000898869,0.000286709],"domain_scores_gemma":[0.9971839,0.00113042,0.000274171,0.0008484225,0.000436587,0.0001265837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002061533,0.0009198828,0.005898236,0.001027094,0.0002164505,0.0008670854,0.0003857895,0.2848749,0.1701139,0.1493244,0.03427963,0.3500312],"study_design_scores_gemma":[0.0001333934,0.0005730072,0.0004466945,0.0001071725,0.00006039083,0.0004518992,0.00006507301,0.8054413,0.1332037,0.03778142,0.02165717,0.00007872168],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04441703,0.001088965,0.9271434,0.0007994861,0.0004211668,0.0001899997,0.0003503937,0.01337703,0.0122126],"genre_scores_gemma":[0.8177038,0.0004211774,0.1701761,0.001337321,0.0001484145,0.0003152121,0.0004872123,0.0008823891,0.008528338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007135502,"threshold_uncertainty_score":0.02387065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01566436840640549,"score_gpt":0.2596997755432,"score_spread":0.2440354071367944,"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."}}