{"id":"W4313484756","doi":"10.1109/dsd57027.2022.00126","title":"Blind Data Adversarial Bit-flip Attack against Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"2022 25th Euromicro Conference on Digital System Design (DSD)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Normalization (sociology); Adversarial system; Artificial neural network; Bit (key); Deep neural networks; Artificial intelligence; Pattern recognition (psychology); Computer security","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001537366,0.0007561638,0.0008098209,0.0003782363,0.001109521,0.001972192,0.008279251,0.0001682764,0.0002157711],"category_scores_gemma":[0.0003056189,0.0008006773,0.0002089024,0.001276955,0.0001546629,0.002278264,0.007118333,0.001550075,0.0003875892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004905986,"about_ca_system_score_gemma":0.000359576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002779152,"about_ca_topic_score_gemma":0.000004305929,"domain_scores_codex":[0.9928866,0.001325345,0.001036008,0.002228749,0.001340541,0.001182736],"domain_scores_gemma":[0.9947555,0.0005274985,0.0007464082,0.003415259,0.0001671219,0.0003881831],"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":[0.0005481879,0.0002239857,0.0002913096,0.00004674738,0.0001479257,0.0008172986,0.0004005063,0.9517305,0.0003703315,0.008935134,0.008661108,0.027827],"study_design_scores_gemma":[0.00190598,0.000405809,0.00007682475,0.00005030921,0.00002940152,0.0001576719,0.000350197,0.9915811,0.00001814856,0.00003225907,0.004559453,0.000832815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008540372,0.0001744457,0.9724249,0.0004089212,0.005148593,0.001441911,0.0002256744,0.001044526,0.01059071],"genre_scores_gemma":[0.9937922,0.000008026165,0.003701922,0.0004626149,0.0005952582,0.00009254718,0.0004597915,0.0001138786,0.0007737843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9852518,"threshold_uncertainty_score":0.9994444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08764770272569537,"score_gpt":0.2796373624652688,"score_spread":0.1919896597395734,"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."}}