{"id":"W2801491268","doi":"10.1515/popets-2018-0024","title":"Privacy-preserving Machine Learning as a Service","year":2018,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":255,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Center for Discrete Mathematics and Theoretical Computer Science; National Science Foundation","keywords":"Computer science; Homomorphic encryption; Encryption; Cloud computing; Machine learning; Artificial intelligence; Artificial neural network; Deep learning; Domain (mathematical analysis); Information privacy; Service provider; Raw data; Service (business); Data mining; Computer security","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":[0.003091524,0.0006072486,0.0009613901,0.0008576461,0.001086555,0.002234174,0.001514936,0.001524346,0.003849978],"category_scores_gemma":[0.008522593,0.0003136855,0.000674089,0.0017186,0.001678303,0.004537273,0.00301779,0.002897348,0.001293149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001812297,"about_ca_system_score_gemma":0.00238016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009278428,"about_ca_topic_score_gemma":0.0006465199,"domain_scores_codex":[0.9947916,0.001795586,0.0003192337,0.0005191924,0.001922204,0.0006522008],"domain_scores_gemma":[0.990348,0.002711674,0.0008371227,0.005038556,0.0008329371,0.0002317631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002253078,0.000808087,0.004262608,0.0003951835,0.0001684644,0.001104394,0.0003476815,0.2919326,0.02584081,0.3541614,0.02593668,0.292789],"study_design_scores_gemma":[0.00008817323,0.00008222467,0.0002959163,0.0000244474,0.0000146131,0.0002960219,0.00005266384,0.8908822,0.01727949,0.0846348,0.00632514,0.00002430501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08266494,0.0008437606,0.8969533,0.003889486,0.0002493143,0.0002475028,0.0007115389,0.003884048,0.01055596],"genre_scores_gemma":[0.9455435,0.0002986728,0.04988483,0.0004426935,0.0001222203,0.0001195262,0.0003063307,0.00007592113,0.003206225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003849978,"threshold_uncertainty_score":0.01634979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01662893650988808,"score_gpt":0.2558164311824623,"score_spread":0.2391874946725742,"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."}}