{"id":"W4416234927","doi":"10.1007/978-3-032-10466-3_34","title":"Federated Learning via TEE-Based Dual-Branch Architecture and Interaction-Aware Pruning","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Pruning; Federated learning; Feature (linguistics); Architecture; Cryptography; Scheme (mathematics); Artificial neural network; Cryptographic primitive","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008275878,0.0005908128,0.0005393648,0.001170479,0.0009822006,0.001352199,0.001342987,0.0003869482,0.00001962184],"category_scores_gemma":[0.000195934,0.0005932786,0.0001145809,0.0009568328,0.0004579144,0.0004766592,0.001035729,0.002010847,0.00001226467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000260617,"about_ca_system_score_gemma":0.0006900049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003866522,"about_ca_topic_score_gemma":0.00005249916,"domain_scores_codex":[0.9961849,0.0001118998,0.000607652,0.001768839,0.0007133038,0.0006134324],"domain_scores_gemma":[0.9970594,0.00131543,0.0003912057,0.0007192986,0.0003479416,0.0001667434],"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":[0.000009983712,0.00002216037,0.000111662,0.0001150529,0.0000165265,0.00003645931,0.0008485641,0.1184905,0.0002087709,0.003779005,0.00001779573,0.8763435],"study_design_scores_gemma":[0.0003089641,0.0001120441,0.00007951488,0.001007663,0.000008864912,0.0000898461,6.240416e-7,0.9723423,0.001373426,0.01954365,0.004508432,0.0006247112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002508352,0.00037884,0.9936522,0.001377357,0.001684244,0.00036121,0.000002119566,0.0003854406,0.001907748],"genre_scores_gemma":[0.781369,0.0000306513,0.2148758,0.002590546,0.0005025644,0.00001637427,0.0000210418,0.00004397384,0.0005500361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8757188,"threshold_uncertainty_score":0.9996845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01370816885321373,"score_gpt":0.2532038482222261,"score_spread":0.2394956793690124,"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."}}