{"id":"W4288087940","doi":"10.48550/arxiv.1910.14107","title":"Investigating Resistance of Deep Learning-based IDS against Adversaries\\n using min-max Optimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence; Intrusion detection system; Deep learning; Robustness (evolution); Machine learning; Artificial neural network; Deep neural networks","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039529,0.001288587,0.0009079748,0.0007264564,0.0004006802,0.0008513039,0.0009436634,0.00124636,0.001232367],"category_scores_gemma":[0.0135238,0.0004400554,0.0006048913,0.0003575665,0.001722869,0.001846576,0.00175407,0.001877832,0.0002177445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001727315,"about_ca_system_score_gemma":0.0007096866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001623673,"about_ca_topic_score_gemma":0.0009756688,"domain_scores_codex":[0.9984061,0.0006999509,0.00008192059,0.000278924,0.0003154571,0.0002177274],"domain_scores_gemma":[0.9909385,0.006861673,0.0008138385,0.0007167881,0.0004393146,0.0002298992],"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":[0.0001967389,0.00004644258,0.001242643,0.00006060385,0.00006339738,0.00003162509,0.00002988059,0.9781711,0.00197044,0.007021832,0.0005315041,0.01063396],"study_design_scores_gemma":[0.000002725737,0.00004502231,0.0001141647,0.000004952607,0.000004762054,0.00000836833,0.000005825989,0.9965233,0.001082365,0.002135748,0.00006989125,0.000002900068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3255278,0.001492533,0.6607127,0.002050448,0.0001324509,0.0001363912,0.0001919691,0.00118863,0.008567111],"genre_scores_gemma":[0.9789984,0.0002315692,0.01918396,0.0001628086,0.00002123446,0.0000450821,0.00007148378,0.00004418383,0.001241431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0039529,"threshold_uncertainty_score":0.0209052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04455363439003174,"score_gpt":0.2029565027623202,"score_spread":0.1584028683722885,"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."}}