{"id":"W2996149581","doi":"10.48550/arxiv.1912.09303","title":"SIGMA : Strengthening IDS with GAN and Metaheuristics Attacks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Robustness (evolution); Adversarial system; Machine learning; Artificial intelligence; Intrusion detection system; Generative grammar; Adversarial machine learning; Metaheuristic; Attack surface; Attack model; Computer security","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001499798,0.0003317868,0.0003463393,0.0002678515,0.000125511,0.0001172262,0.001039909,0.0002230222,0.000007852383],"category_scores_gemma":[0.00003304664,0.0003470012,0.00007892604,0.0003923834,0.0001561655,0.0004001532,0.001389431,0.0006446361,0.00001194099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000120425,"about_ca_system_score_gemma":0.0001103048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004237738,"about_ca_topic_score_gemma":0.00002206778,"domain_scores_codex":[0.9982522,0.00008214417,0.0001606285,0.001113349,0.0001024612,0.0002892312],"domain_scores_gemma":[0.9980555,0.00014039,0.0002709758,0.001227594,0.0001718098,0.0001337847],"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":[0.0001728638,0.0001779025,0.01353689,0.0005163358,0.0005027469,0.001343632,0.001085306,0.6949054,0.0002481845,0.2704951,0.0003781579,0.01663752],"study_design_scores_gemma":[0.001038907,0.0005950998,0.001890023,0.0003773458,0.0002437377,0.00006650482,0.0002263348,0.8884323,0.006331007,0.09446803,0.004512822,0.001817889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06448586,0.00005380562,0.9321963,0.00003047206,0.000198679,0.000270479,0.000009301531,0.0007008042,0.002054318],"genre_scores_gemma":[0.9640858,0.000133461,0.03470346,0.00004282825,0.00003244529,0.000001177466,0.000004326032,0.00002537706,0.0009711565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8995999,"threshold_uncertainty_score":0.9998982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420461988631143,"score_gpt":0.1853549323461231,"score_spread":0.1411503124598116,"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."}}