{"id":"W4392309419","doi":"10.1007/978-3-031-54204-6_18","title":"AddShare: A Privacy-Preserving Approach for Federated Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Federated learning; Information privacy; Safeguard; Private information retrieval; Machine learning; Artificial intelligence; Computation; Information sensitivity; Simple (philosophy); Training set; Data mining; Computer security; Algorithm","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":[0.00348441,0.0007313814,0.001222126,0.001240125,0.002144273,0.004835104,0.004044448,0.002307869,0.009446158],"category_scores_gemma":[0.007076801,0.0006207636,0.00167907,0.001867742,0.002240565,0.009597107,0.009799997,0.004891056,0.002924488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001523744,"about_ca_system_score_gemma":0.00232532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109911,"about_ca_topic_score_gemma":0.001572273,"domain_scores_codex":[0.9958745,0.001048916,0.0002186245,0.0007185673,0.001680184,0.0004591764],"domain_scores_gemma":[0.9954875,0.0008908343,0.0001411926,0.002939205,0.0003551082,0.0001861258],"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":[0.0008789315,0.0004623973,0.0006714864,0.0002449662,0.0001562997,0.0002094559,0.0003806636,0.03599391,0.005160435,0.4417127,0.03175937,0.4823694],"study_design_scores_gemma":[0.00005963797,0.0001111566,0.0002526995,0.00007528736,0.00006114379,0.0004613757,0.0001294797,0.2808944,0.02451958,0.6261396,0.06723045,0.00006524022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003289606,0.0001857271,0.9866058,0.0004274884,0.0001240123,0.00008402426,0.0002186527,0.004303723,0.004760902],"genre_scores_gemma":[0.2335259,0.0005551671,0.7291459,0.001026032,0.0002402988,0.0003590539,0.001247908,0.0009731507,0.03292666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009446158,"threshold_uncertainty_score":0.03160048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03490441550461065,"score_gpt":0.2714505123681983,"score_spread":0.2365460968635877,"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."}}