{"id":"W3111292980","doi":"10.1145/3453169","title":"Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Asynchronous communication; Edge device; Overhead (engineering); Enhanced Data Rates for GSM Evolution; Edge computing; Cloud computing; Node (physics); The Internet; Industrial Internet; Distributed computing; Asynchronous learning; Computer network; Computer security; Artificial intelligence; Internet of Things","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003265653,0.0002054579,0.0003290033,0.0004590798,0.0001491857,0.00011998,0.01038911,0.0004755352,0.00003611884],"category_scores_gemma":[0.0070852,0.0002119198,0.0000805467,0.0008179793,0.0003735618,0.0002281356,0.005609665,0.0009163928,0.000006996607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011311,"about_ca_system_score_gemma":0.000113772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005021,"about_ca_topic_score_gemma":0.00003942643,"domain_scores_codex":[0.9983599,0.00009497641,0.0004683637,0.0005920323,0.0001751425,0.0003095787],"domain_scores_gemma":[0.9948764,0.0004066282,0.0002051363,0.004207445,0.0002627901,0.00004158891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002810705,0.000979221,0.0003749985,0.0001317483,0.0006208142,0.00003705222,0.001366589,0.0004307785,0.01167684,0.03942749,0.02270817,0.9219652],"study_design_scores_gemma":[0.002148557,0.001038658,0.00007126496,0.0004614462,0.00006175888,0.0001262296,0.0009754896,0.3734773,0.5440097,0.05940835,0.01766752,0.0005537184],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08163068,0.0002750002,0.8918189,0.02465047,0.0002625019,0.0002569123,0.0000142761,0.0008998285,0.000191417],"genre_scores_gemma":[0.8205017,0.00008211719,0.1790255,0.00008121366,0.000004749718,0.00006747201,0.00001564319,0.00001641578,0.0002051072],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9214115,"threshold_uncertainty_score":0.9949651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0536822248169167,"score_gpt":0.2980146254981496,"score_spread":0.2443324006812329,"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."}}