{"id":"W3004069267","doi":"10.1109/globalsip45357.2019.8969416","title":"Deep Learning-Based Detection of Fake Task Injection in Mobile Crowdsensing","year":2019,"lang":"en","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Deep belief network; Deep learning; Computer science; Autoencoder; Artificial intelligence; Perceptron; Mobile device; Leverage (statistics); Restricted Boltzmann machine; Boltzmann machine; Machine learning; Multilayer perceptron; Artificial neural network; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0004390602,0.0001329649,0.0002053939,0.0003090086,0.00007240086,0.00008087498,0.0001832106,0.0001009068,0.00001700726],"category_scores_gemma":[0.00005037629,0.000132822,0.00007596492,0.000685796,0.00002952015,0.0002617781,0.00006211306,0.0002454494,0.00005380157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007835694,"about_ca_system_score_gemma":0.00003984912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002545348,"about_ca_topic_score_gemma":0.0002272778,"domain_scores_codex":[0.9986994,0.0001281048,0.0003069623,0.0003803793,0.000225053,0.0002601238],"domain_scores_gemma":[0.9991903,0.0001276332,0.000136588,0.0004036894,0.00009606608,0.00004576315],"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":[0.00001994788,0.00007051136,0.008523745,0.00004851366,0.000006484704,0.000005246082,0.0007629876,0.5923568,0.2338241,0.0001732764,0.000004643516,0.1642037],"study_design_scores_gemma":[0.0004510235,0.0003116149,0.004643455,0.00005221902,0.0000027715,0.00001783621,0.000219602,0.8671791,0.1263549,0.00007319968,0.0005242973,0.0001700061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.590645,0.00004775585,0.4076951,0.00001211708,0.0002534794,0.0001450818,4.592118e-8,0.0001369954,0.001064481],"genre_scores_gemma":[0.9966146,0.000002040006,0.003037559,0.00005464847,0.00002296381,0.000006041572,9.668945e-7,0.00001252761,0.0002486117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4059697,"threshold_uncertainty_score":0.5416325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004766400880207423,"score_gpt":0.2050397767114494,"score_spread":0.200273375831242,"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."}}