{"id":"W3093672075","doi":"10.1109/iscc50000.2020.9219661","title":"Knowledge-Based Machine Learning Boosting for Adversarial Task Detection in Mobile Crowdsensing","year":2020,"lang":"en","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; AdaBoost; Machine learning; Boosting (machine learning); Decision tree; Mobile device; Exploit; Artificial intelligence; Feature selection; Task (project management); Support vector machine; Computer security; World Wide Web; Engineering","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":[0.0005113095,0.0002010879,0.0002521607,0.0001457041,0.0003173672,0.000227979,0.0002739344,0.00009878639,0.000006639649],"category_scores_gemma":[0.0004765114,0.0002067877,0.0001188608,0.000610727,0.00003072351,0.0002688754,0.0001254503,0.0003252696,0.00002299316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008567428,"about_ca_system_score_gemma":0.00009679358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008956261,"about_ca_topic_score_gemma":0.0001389946,"domain_scores_codex":[0.9983496,0.0001317237,0.0003523914,0.0005882734,0.0001530856,0.0004249162],"domain_scores_gemma":[0.9989951,0.0004201106,0.0001115438,0.0002286083,0.0001014727,0.000143163],"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":[0.0001668794,0.0001116518,0.001092905,0.0001783301,0.00002170537,0.00003288093,0.004991638,0.176035,0.1993005,0.0004774174,0.0001726637,0.6174183],"study_design_scores_gemma":[0.001157522,0.0002497475,0.00006163203,0.00004507453,0.000006811235,0.000006138338,0.0001190429,0.9306391,0.05774976,0.00004291536,0.009680757,0.0002414844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08111988,0.0001857461,0.9159471,0.0003495892,0.0003818329,0.0004033041,9.634547e-7,0.0005445501,0.001066979],"genre_scores_gemma":[0.9705532,0.000001479118,0.02868491,0.0003686112,0.0002579356,0.00002488912,0.000004544772,0.00002528848,0.00007910708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8894334,"threshold_uncertainty_score":0.8432558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01890668782989297,"score_gpt":0.2440819707516191,"score_spread":0.2251752829217261,"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."}}