{"id":"W4200333262","doi":"10.1016/j.future.2021.11.032","title":"Differentially private facial obfuscation via generative adversarial networks","year":2021,"lang":"en","type":"article","venue":"Future Generation Computer Systems","topic":"Face recognition and analysis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Obfuscation; Computer science; Task (project management); Adversarial system; Computer security; Human–computer interaction; Process (computing); Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001925456,0.0002602092,0.0003315246,0.0001265556,0.000365257,0.00098499,0.0004029207,0.000188491,0.00004162415],"category_scores_gemma":[0.000005792485,0.0002463348,0.0001862473,0.0005771119,0.00001687491,0.0005193138,0.0001851771,0.0001751239,0.00007761885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007939462,"about_ca_system_score_gemma":0.0001095249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001351335,"about_ca_topic_score_gemma":0.00006761823,"domain_scores_codex":[0.9976217,0.0004754169,0.0005010626,0.0006848048,0.000427364,0.0002896124],"domain_scores_gemma":[0.9986089,0.00002490282,0.0002164995,0.0005345988,0.0004711745,0.0001438958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001588665,0.0003718129,0.0002711655,0.00006625048,0.0007018473,0.0001034194,0.001855055,0.2657576,0.02415778,0.0615195,0.1867145,0.4584651],"study_design_scores_gemma":[0.0004782474,0.0000337746,0.0001652139,0.00001337233,0.00002417137,0.00003622958,0.00001516757,0.9271394,0.00204664,0.00001330462,0.06975038,0.0002841315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.001757717,0.0005571158,0.9306383,0.001036713,0.06550645,0.0002062496,0.000007116119,0.000194022,0.00009636019],"genre_scores_gemma":[0.3614337,0.0002881168,0.1987306,0.003335652,0.4318396,0.0001861374,0.002408825,0.00007066585,0.001706681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7319077,"threshold_uncertainty_score":0.9999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01309810059167782,"score_gpt":0.2117237539068038,"score_spread":0.198625653315126,"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."}}