{"id":"W4385412128","doi":"10.1109/eurosp57164.2023.00023","title":"Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Differential privacy; Computer science; Data aggregator; Differential (mechanical device); Federated learning; Information privacy; Computer security; Data mining; Computer network; Artificial intelligence","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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005396589,0.0001509979,0.000167282,0.0002902245,0.000180948,0.0006033485,0.01072738,0.0001075623,0.00001750953],"category_scores_gemma":[0.008521677,0.0001294547,0.000007753601,0.0009861476,0.0000764096,0.001425329,0.0821917,0.0004101424,0.00001605007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002608505,"about_ca_system_score_gemma":0.00005638369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005447755,"about_ca_topic_score_gemma":0.00009333949,"domain_scores_codex":[0.9982891,0.0001091325,0.0002297471,0.0007412586,0.0002928078,0.0003379747],"domain_scores_gemma":[0.9964497,0.0001901553,0.0001198109,0.003161576,0.00003524113,0.000043513],"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":[0.00004820997,0.0000671514,0.4210005,0.00009999649,0.0001435357,0.0001989795,0.001359463,0.00006185793,0.001155612,0.001555828,0.03089792,0.543411],"study_design_scores_gemma":[0.001148109,0.00008369576,0.03698014,0.000183597,0.000008331248,0.00008047112,0.000406262,0.9372382,0.003023721,0.0202358,0.0002456477,0.0003660173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.925513,0.00001698301,0.06534382,0.007145168,0.0001232239,0.0001761489,0.00001463379,0.001513095,0.0001539757],"genre_scores_gemma":[0.8347617,0.00003305695,0.1648861,0.00002963263,0.00001778159,0.000006968435,0.0002172328,0.0000119858,0.00003551214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9371763,"threshold_uncertainty_score":0.9998299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05261085302713452,"score_gpt":0.2788809764056963,"score_spread":0.2262701233785618,"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."}}