{"id":"W4388662069","doi":"10.1145/3581784.3607084","title":"Structural Coding: A Low-Cost Scheme to Protect CNNs from Large-Granularity Memory Faults","year":2023,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Meta; Alliance de recherche numérique du Canada; Intel Corporation","keywords":"Dram; Granularity; Computer science; Convolutional neural network; Coding (social sciences); Scheme (mathematics); Embedded system; Distributed computing; Computer engineering; Computer hardware; Artificial intelligence; Operating system","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":[0.0005571741,0.0007443449,0.0004340631,0.0004401101,0.0004814225,0.0005631513,0.001637844,0.0008681969,0.002661973],"category_scores_gemma":[0.002982464,0.0002330827,0.0003560077,0.0003243601,0.0009521255,0.001568222,0.00176958,0.001297603,0.0005737069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006657258,"about_ca_system_score_gemma":0.001067437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001320824,"about_ca_topic_score_gemma":0.002305364,"domain_scores_codex":[0.9995667,0.00005282749,0.00002486908,0.00007863245,0.0001869503,0.00008998952],"domain_scores_gemma":[0.9987675,0.0003288643,0.0001881539,0.0004211147,0.0002424153,0.00005207644],"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":[0.0007998909,0.0001584553,0.001263476,0.0003470627,0.0001295618,0.0004055574,0.0002496992,0.3668434,0.1631985,0.1371962,0.01816551,0.3112427],"study_design_scores_gemma":[0.00004497107,0.0002888445,0.0003433358,0.00004175462,0.00005436748,0.0001634237,0.00003175991,0.9040813,0.05220306,0.03742004,0.005295157,0.00003201255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07050341,0.0007704936,0.9166946,0.0007732839,0.0003296789,0.000128752,0.0002223629,0.00264949,0.007927977],"genre_scores_gemma":[0.9336001,0.0003475281,0.06031688,0.0003630031,0.00009769293,0.00008951283,0.0002038477,0.0001016953,0.004879826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002661973,"threshold_uncertainty_score":0.008905172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0242408235099306,"score_gpt":0.291877369301996,"score_spread":0.2676365457920654,"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."}}