{"id":"W2798248638","doi":"10.1145/3190619.3190637","title":"Robustness of deep autoencoder in intrusion detection under adversarial contamination","year":2018,"lang":"en","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Autoencoder; Robustness (evolution); Computer science; Artificial intelligence; Adversarial system; Deep learning; Machine learning; Intrusion detection system; Adversarial machine learning; Anomaly detection; Artificial neural network; Data mining; 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":[0.0003421639,0.00008559441,0.0001175573,0.0002296654,0.00008871037,0.00003323005,0.0002472262,0.0001169105,0.0001681913],"category_scores_gemma":[0.00002983882,0.00008029001,0.00003425874,0.0005672653,0.00006501345,0.0006525068,0.0001308914,0.0001073219,0.00001806425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007933969,"about_ca_system_score_gemma":0.00002349402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001462155,"about_ca_topic_score_gemma":0.001768666,"domain_scores_codex":[0.9990214,0.00009311865,0.0002642072,0.000250046,0.0002149641,0.000156342],"domain_scores_gemma":[0.9994152,0.00004925633,0.0001020299,0.0002358752,0.0001642846,0.00003340593],"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":[0.0002022044,0.0002608074,0.000191388,0.00002576083,0.00001793062,0.00000249688,0.001696056,0.07757344,0.01371127,0.05910704,0.0001560731,0.8470556],"study_design_scores_gemma":[0.0005054418,0.0002240682,0.002758796,0.00001247208,0.000002376901,0.000006014057,0.00004724347,0.963853,0.02973016,0.00247204,0.0002921769,0.00009623405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1188946,0.000009747305,0.8777063,0.0001265632,0.001300142,0.0001179662,9.536313e-8,0.00007953594,0.001765025],"genre_scores_gemma":[0.987737,0.000008392655,0.01187394,0.00006941379,0.0002407584,0.000005605778,7.363461e-7,0.000004270787,0.00005990035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8862795,"threshold_uncertainty_score":0.3274132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0100241664206916,"score_gpt":0.2301784300217925,"score_spread":0.2201542636011009,"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."}}