{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001002853,0.001491973,0.001163846,0.001021368,0.001559619,0.0006032388,0.004052952,0.001281448,0.0007856326],"category_scores_gemma":[0.0005958666,0.001917353,0.0007525334,0.002199514,0.001373326,0.001340015,0.00307899,0.002564186,0.0001600436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001365499,"about_ca_system_score_gemma":0.001295758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000372722,"about_ca_topic_score_gemma":0.00002088523,"domain_scores_codex":[0.991575,0.001604957,0.0008899576,0.003908975,0.0005462628,0.001474818],"domain_scores_gemma":[0.9934933,0.0007991447,0.001649924,0.002691054,0.0006921052,0.0006745136],"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":[0.0006325489,0.0001737602,0.001716431,0.00009519744,0.0001806405,0.000479918,0.000357674,0.9927047,0.0000463125,0.003013802,0.00004173315,0.0005572264],"study_design_scores_gemma":[0.003307944,0.0005406647,0.0002010223,0.0004170467,0.0003952539,0.00001781057,0.0001925158,0.9925782,0.0001805037,0.0003408874,0.0000977992,0.001730328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1809071,0.00001287479,0.8108204,0.0001124912,0.005717467,0.000952787,0.00004379286,0.0004213422,0.001011794],"genre_scores_gemma":[0.9622022,0.00002122043,0.03601666,0.0003129304,0.0009930121,0.000001113049,0.0000664029,0.0001224436,0.000264037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7812951,"threshold_uncertainty_score":0.9997829,"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."}}