{"id":"W3048295601","doi":"10.1109/tnse.2020.3014385","title":"Learning in the Air: Secure Federated Learning for UAV-Assisted Crowdsensing","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":305,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Federated learning; Crowdsensing; Differential privacy; Reinforcement learning; Data sharing; Information privacy; Artificial intelligence; Vulnerability (computing); Computer security; Distributed computing; Machine learning; Data mining","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":[0.001879518,0.0005906718,0.0008906276,0.0003794846,0.001001506,0.001017209,0.001611745,0.001083176,0.001228735],"category_scores_gemma":[0.003871376,0.0002243496,0.000557859,0.0005009297,0.001240794,0.002017905,0.003020668,0.001296108,0.0002399251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009467631,"about_ca_system_score_gemma":0.001860899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003792454,"about_ca_topic_score_gemma":0.003257758,"domain_scores_codex":[0.9985998,0.0003442497,0.00007935189,0.0003325483,0.0004046886,0.0002392219],"domain_scores_gemma":[0.9976063,0.0008770218,0.0003119489,0.0006831601,0.0003542076,0.0001674284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004259516,0.0001573369,0.001675078,0.0001025683,0.0000562244,0.0003626715,0.0002873073,0.8668625,0.007486909,0.03197997,0.001626269,0.08897717],"study_design_scores_gemma":[0.00001407649,0.00003467012,0.00008113552,0.000004705121,0.000004441179,0.00002988728,0.00001568215,0.9881556,0.001257253,0.009871109,0.0005253169,0.000006087218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04060836,0.0002215659,0.9562808,0.0002801128,0.00005855714,0.00007978557,0.00005398664,0.0005923539,0.001824436],"genre_scores_gemma":[0.9665982,0.00009175363,0.03201533,0.00009171907,0.00001745225,0.00006297557,0.00004904342,0.00001678371,0.001056872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003792454,"threshold_uncertainty_score":0.009939909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02362232932625817,"score_gpt":0.2352258112228885,"score_spread":0.2116034818966304,"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."}}