{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005781654,0.0002613135,0.0002856754,0.0001986775,0.0003984582,0.0002046958,0.001526497,0.0001244976,0.0001847864],"category_scores_gemma":[0.0007876864,0.0002357632,0.0001055938,0.001251669,0.00003375701,0.0005538871,0.001442907,0.0005168647,0.0008240882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000852397,"about_ca_system_score_gemma":0.00007903312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005738487,"about_ca_topic_score_gemma":0.0001272803,"domain_scores_codex":[0.9974933,0.0001497594,0.0002933617,0.0007965699,0.0005636282,0.0007033296],"domain_scores_gemma":[0.9984524,0.0002458526,0.0000882319,0.0008747943,0.00009308936,0.000245579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005761337,0.0004052766,0.0945054,0.0004542528,0.0006606713,0.002110779,0.0412997,0.2408619,0.06229243,0.2688735,0.03785377,0.2501062],"study_design_scores_gemma":[0.00106309,0.0000397854,0.02299463,0.00005203703,0.000006864528,0.000004422131,0.0001946152,0.9652882,0.004117057,0.003598788,0.002084359,0.0005561525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3060482,0.000004792129,0.6869524,0.002035538,0.001483003,0.0006729243,0.000018977,0.00139276,0.001391351],"genre_scores_gemma":[0.9041256,7.091544e-7,0.09422431,0.000557482,0.0002796923,0.00006083541,0.00003070412,0.00002569929,0.000694932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7244263,"threshold_uncertainty_score":0.9999539,"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."}}