{"id":"W3097342189","doi":"10.3390/sym12111805","title":"Detecting Shilling Attacks Using Hybrid Deep Learning Models","year":2020,"lang":"en","type":"article","venue":"Symmetry","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Ryerson University","keywords":"Computer science; Deep learning; Robustness (evolution); Artificial intelligence; Convolutional neural network; Machine learning; Architecture; Recommender system; Attack model; Artificial neural network; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003553692,0.0001572461,0.0002191486,0.00009350078,0.0002480645,0.0002473222,0.0005856775,0.00005633196,0.00000448188],"category_scores_gemma":[0.00006365027,0.0001564538,0.00009560068,0.000408422,0.00001161618,0.0006531755,0.0003540826,0.0003596935,0.00001470618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004973508,"about_ca_system_score_gemma":0.00002209328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006631897,"about_ca_topic_score_gemma":0.000001228391,"domain_scores_codex":[0.9986192,0.0001061808,0.0002853324,0.0004374041,0.0002241927,0.0003276772],"domain_scores_gemma":[0.9993231,0.00007826406,0.0001385128,0.0002694487,0.00005015339,0.0001404817],"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":[0.00001281375,0.00006415969,0.008438249,0.0003567183,0.0001710453,0.0002407587,0.007196832,0.03104884,0.0152495,0.04976054,0.0005659059,0.8868946],"study_design_scores_gemma":[0.00009061664,0.00004633871,0.0000161296,0.00003982631,0.000004351508,0.00003901757,0.00009427808,0.9825681,0.01261555,0.003393664,0.0008852358,0.0002068836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03024898,0.0003916138,0.9635868,0.0003067729,0.0002178124,0.0001078937,3.761e-7,0.0007136341,0.004426106],"genre_scores_gemma":[0.881467,0.000009662367,0.1178893,0.0004140286,0.0001859512,0.000003782308,6.038628e-7,0.00001979228,0.000009922172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9515193,"threshold_uncertainty_score":0.638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0781143189336796,"score_gpt":0.2719299946488173,"score_spread":0.1938156757151377,"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."}}