{"id":"W4318541558","doi":"10.1145/3575693.3575738","title":"HuffDuff: Stealing Pruned DNNs from Sparse Accelerators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Exploit; Computer science; Edge device; Enhanced Data Rates for GSM Evolution; Side channel attack; Channel (broadcasting); State (computer science); Edge computing; Deep learning; Power (physics); Distributed computing; Computer network; Artificial intelligence; Computer security; Operating system; Cloud computing; Cryptography; Programming language","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":[0.000883803,0.0007395511,0.0006219154,0.000376855,0.0003654764,0.0006903813,0.001461445,0.001231143,0.004252095],"category_scores_gemma":[0.004925034,0.0004023193,0.0004600447,0.0002801522,0.001250938,0.001953657,0.002207533,0.001786715,0.0008885941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007989202,"about_ca_system_score_gemma":0.0007916311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002293971,"about_ca_topic_score_gemma":0.004219102,"domain_scores_codex":[0.999483,0.0001138459,0.00002210788,0.00008297247,0.0001940014,0.0001040891],"domain_scores_gemma":[0.9988273,0.0005897659,0.00008052589,0.0003307322,0.0001151873,0.00005662279],"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":[0.0005014816,0.00007341272,0.001048911,0.0001143412,0.00007517589,0.0004187351,0.0001002413,0.8287262,0.01317204,0.05114698,0.007895148,0.09672735],"study_design_scores_gemma":[0.00001271531,0.00003572149,0.00005118273,0.00001073012,0.000005367038,0.00003593295,0.000007699659,0.9772223,0.003791717,0.01803861,0.000782362,0.00000570563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1279539,0.0009021088,0.8495436,0.001221211,0.0003168765,0.00008728297,0.0002916777,0.006131796,0.01355155],"genre_scores_gemma":[0.9138813,0.0001929858,0.07833169,0.0004827442,0.00004443265,0.00006132355,0.0002920557,0.0003948722,0.006318548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004252095,"threshold_uncertainty_score":0.01422471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0318325200345579,"score_gpt":0.2771317073615917,"score_spread":0.2452991873270338,"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."}}