{"id":"W2995755899","doi":"10.48550/arxiv.1912.06409","title":"Potential adversarial samples for white-box attacks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adversarial system; White (mutation); Computer security; White box; Computer science; Artificial intelligence; 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":[0.0004986021,0.0005712815,0.000650814,0.0003798509,0.0003413342,0.0002551401,0.003768555,0.0006557148,0.00008870164],"category_scores_gemma":[0.0001921903,0.0006927278,0.0005046259,0.0004521766,0.0001729416,0.000680005,0.004491571,0.001091747,0.0001464837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003422054,"about_ca_system_score_gemma":0.0004938369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001315267,"about_ca_topic_score_gemma":0.00002026184,"domain_scores_codex":[0.9964973,0.0002459799,0.0003466734,0.00198596,0.0002048506,0.0007192031],"domain_scores_gemma":[0.9966885,0.0003129357,0.0005413545,0.001950109,0.00029814,0.0002089367],"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":[0.0001677889,0.00005177436,0.001684831,0.0001261181,0.0001399497,0.00008786498,0.0002309881,0.9180642,0.00002622424,0.07787263,0.001086744,0.0004608875],"study_design_scores_gemma":[0.001803822,0.0001200844,0.000848617,0.00009613227,0.0001796149,0.000006303711,0.0001114444,0.9633164,0.00003772315,0.02922359,0.003361272,0.0008950395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02170808,0.00003427069,0.9695687,0.0003021314,0.005378908,0.0008855279,0.00006242657,0.0004720495,0.001587966],"genre_scores_gemma":[0.9576384,0.00003301035,0.03806552,0.0001256115,0.0007135991,0.000003163586,0.00009977594,0.00005595154,0.00326493],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9359304,"threshold_uncertainty_score":0.9995524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0579504687322764,"score_gpt":0.213355144855566,"score_spread":0.1554046761232896,"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."}}