{"id":"W7036099227","doi":"","title":"Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge","year":2024,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Skin Protection and Aging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada)","funders":"","keywords":"Adversarial system; Adversary; Domain (mathematical analysis); Threat model; Order (exchange); Attack model; Key (lock); Adversarial machine learning","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":[0.00022876,0.0003071993,0.0006246801,0.0008900044,0.0002070508,0.00002588573,0.0002347209,0.0003411641,0.0008042773],"category_scores_gemma":[0.00007178417,0.0003416832,0.0003043371,0.0007661947,0.0000344523,0.00009887102,0.0001162879,0.000721798,0.0004793722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001829898,"about_ca_system_score_gemma":0.0001772249,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131655,"about_ca_topic_score_gemma":0.01392249,"domain_scores_codex":[0.998524,0.00007679043,0.0001821264,0.0006181045,0.0003104561,0.0002885714],"domain_scores_gemma":[0.9989669,0.00006176357,0.0001266084,0.0004213809,0.000197096,0.0002263042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001994951,0.000779181,0.003098988,0.00137843,0.001662794,0.0008187096,0.9626045,0.00002183951,0.002772774,0.0001273046,0.00362786,0.02111269],"study_design_scores_gemma":[0.002038571,0.0009517984,0.01775602,0.002984831,0.002257005,0.00001402656,0.9669437,0.0001296455,0.0008979355,0.0001833559,0.005277972,0.0005651509],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947336,0.0003486485,0.0001565605,0.0005457202,0.001420096,0.001110628,0.00001316697,0.0001983141,0.00147327],"genre_scores_gemma":[0.6030759,0.00004260867,0.003111383,0.00003144382,0.0003116764,0.000002530769,0.0001721235,0.00006452519,0.3931878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3917145,"threshold_uncertainty_score":0.9999035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735830518735912,"score_gpt":0.2684269584258567,"score_spread":0.2510686532384975,"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."}}