{"id":"W4297233070","doi":"10.48550/arxiv.1805.12302","title":"Adversarial Attacks on Face Detectors using Neural Net based Constrained\\n Optimization","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Adversarial system; Generator (circuit theory); Robustness (evolution); Artificial intelligence; Detector; Face (sociological concept); Scalability; Artificial neural network; Machine learning; JPEG; Pattern recognition (psychology); Data compression","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":[0.001447223,0.001248316,0.000820733,0.0005307344,0.000422153,0.0007295694,0.001169568,0.001351616,0.002473238],"category_scores_gemma":[0.004341141,0.0004577551,0.000707555,0.0002687428,0.001906497,0.001531235,0.00199734,0.002223601,0.0005713649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001487572,"about_ca_system_score_gemma":0.0008509812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003090391,"about_ca_topic_score_gemma":0.003396648,"domain_scores_codex":[0.9991089,0.0002643985,0.00002929398,0.0002113438,0.0002568096,0.0001293405],"domain_scores_gemma":[0.9986681,0.0007893794,0.0001369983,0.0002378676,0.00011162,0.00005597811],"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":[0.0001530127,0.00006997515,0.0006183007,0.00003744992,0.00005728366,0.0001088862,0.00003664647,0.922848,0.009095292,0.02124287,0.002533939,0.04319827],"study_design_scores_gemma":[0.000004280566,0.00001724453,0.00005632601,0.00000275928,0.000002153069,0.00001497638,0.000002279014,0.9941797,0.001863977,0.00364173,0.000211155,0.000003453033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06687428,0.0002982304,0.9231772,0.0007897459,0.00008217393,0.00008374625,0.0001037766,0.001748967,0.006841878],"genre_scores_gemma":[0.8537599,0.0001945194,0.1373827,0.0006371225,0.0000560295,0.0001154426,0.0002199503,0.0002107573,0.007423414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003090391,"threshold_uncertainty_score":0.01079309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08441488832756999,"score_gpt":0.2249147760886206,"score_spread":0.1404998877610507,"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."}}