{"id":"W2946062220","doi":"10.23919/date.2019.8714862","title":"PUFs Deep Attacks: Enhanced modeling attacks using deep learning techniques to break the security of double arbiter PUFs","year":2019,"lang":"en","type":"article","venue":"","topic":"Physical Unclonable Functions (PUFs) and Hardware Security","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Arbiter; Computer science; Deep learning; Cryptography; Key (lock); Authentication (law); Artificial intelligence; Hardware security module; Embedded system; Computer security; Machine learning; Computer hardware","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"],"consensus_categories":[],"category_scores_codex":[0.0006441278,0.0003487133,0.0004964029,0.0002065677,0.0003640403,0.0002805151,0.001323176,0.0001585974,0.0001548516],"category_scores_gemma":[0.00005263979,0.0002636651,0.0002503698,0.001018889,0.00006530589,0.001101444,0.0009478055,0.0006138906,0.0001589315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327352,"about_ca_system_score_gemma":0.00009558331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005711323,"about_ca_topic_score_gemma":0.0001432548,"domain_scores_codex":[0.9972175,0.0001362367,0.0005537958,0.0008176,0.0006047639,0.0006701177],"domain_scores_gemma":[0.9978281,0.0001819381,0.0001863604,0.001154401,0.0004577519,0.0001914203],"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":[0.0007178194,0.00198032,0.002921236,0.0007499959,0.0005761324,0.00003193488,0.03188793,0.4231457,0.2637074,0.1819344,0.0007498655,0.09159721],"study_design_scores_gemma":[0.0004401946,0.0002088152,0.00005485739,0.0001160864,0.00002580845,0.00001409431,0.0002909169,0.8969668,0.09040046,0.008641005,0.002346062,0.0004949322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3193845,0.00006919895,0.6689314,0.0003055351,0.0002473521,0.0005170431,0.000001472206,0.0003528671,0.01019058],"genre_scores_gemma":[0.9690447,0.00001710879,0.02970999,0.0006205806,0.0001824371,0.00004079899,0.000003531595,0.0000290646,0.0003517256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6496603,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01565376379151446,"score_gpt":0.2662223879747206,"score_spread":0.2505686241832061,"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."}}