{"id":"W4405440279","doi":"10.1109/pst62714.2024.10788064","title":"Poisoning and Evasion: Deep Learning-Based NIDS under Adversarial Attacks","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of New Brunswick","funders":"","keywords":"Adversarial system; Evasion (ethics); Computer science; Computer security; Artificial intelligence; Deep learning; Machine learning; Medicine","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":[0.003748162,0.0009410348,0.001184592,0.0009900371,0.0004753672,0.0008788233,0.001908811,0.001481695,0.0007209644],"category_scores_gemma":[0.006122343,0.0002815054,0.0007236073,0.0004422094,0.001545499,0.002008883,0.002210183,0.002049063,0.0002393151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001462136,"about_ca_system_score_gemma":0.001081059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00333095,"about_ca_topic_score_gemma":0.002201039,"domain_scores_codex":[0.9986256,0.0004394493,0.00008070073,0.0002385986,0.0003723885,0.0002432665],"domain_scores_gemma":[0.9973125,0.00123033,0.0003742271,0.0005325687,0.0003494563,0.0002009242],"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":[0.0006361383,0.0004640667,0.01041447,0.0001339111,0.0002051664,0.0002943638,0.0001204816,0.8597882,0.004088379,0.01152054,0.00688754,0.1054468],"study_design_scores_gemma":[0.00001349468,0.00007418431,0.0003540559,0.000006559864,0.00001159182,0.00004894608,0.000009909549,0.9941294,0.001565175,0.003354858,0.0004246375,0.000007150737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4478806,0.003327591,0.5239716,0.003223162,0.0004556294,0.0004415328,0.0006360431,0.01055297,0.009510833],"genre_scores_gemma":[0.9605963,0.0002422467,0.03697715,0.000406124,0.00003295352,0.0000568497,0.000339844,0.00005433199,0.001294174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003748162,"threshold_uncertainty_score":0.01982242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009398891778544322,"score_gpt":0.2638176907547325,"score_spread":0.2544187989761882,"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."}}