{"id":"W4385522629","doi":"10.56553/popets-2023-0122","title":"Privacy-Preserving Federated Recurrent Neural Networks","year":2023,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Homomorphic encryption; Encryption; Recurrent neural network; Clipping (morphology); Scheme (mathematics); Artificial neural network; Artificial intelligence; Theoretical computer science; Computer engineering; Computer network; Mathematics","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":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001432399,0.0008549964,0.0007450114,0.001585222,0.0009108194,0.001398242,0.05704531,0.0007859036,0.000009996796],"category_scores_gemma":[0.08470977,0.0008034623,0.0001973407,0.006348329,0.0003319826,0.002308635,0.1915579,0.001954619,0.0002415754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003784472,"about_ca_system_score_gemma":0.00007459545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001246419,"about_ca_topic_score_gemma":0.000003005977,"domain_scores_codex":[0.993611,0.00003874473,0.0009987968,0.002228604,0.001046801,0.002076001],"domain_scores_gemma":[0.9908773,0.0005098851,0.000588537,0.007470085,0.0004138011,0.0001403472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007658204,0.0002716139,0.004475765,0.0003768144,0.000168755,0.0001518692,0.0004800248,0.0002861708,0.01495418,0.02034362,0.6353754,0.3230392],"study_design_scores_gemma":[0.0004733528,0.0003689286,0.0006705878,0.0004384991,0.00001453537,0.00004233349,0.0004899456,0.7541244,0.07905143,0.1590443,0.00425562,0.00102609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5714099,0.0007076974,0.1415672,0.1485999,0.002467962,0.001838489,0.0000208447,0.1315567,0.001831304],"genre_scores_gemma":[0.9160034,0.0007576293,0.08233073,0.0002404723,0.0000914301,0.0003672423,0.00002882216,0.00009894038,0.00008132663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7538382,"threshold_uncertainty_score":0.9996384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03221086432291834,"score_gpt":0.2783030673789672,"score_spread":0.2460922030560489,"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."}}