{"id":"W3086697721","doi":"10.48550/arxiv.1905.05137","title":"Analyzing Adversarial Attacks Against Deep Learning for Intrusion\\n Detection in IoT Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Intrusion detection system; Adversarial system; Artificial intelligence; Deep learning; Internet of Things; Machine learning; Artificial neural network; Computer security; Resilience (materials science); Robustness (evolution); SAFER; Data mining","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":[0.00294544,0.0009002841,0.0006563644,0.0009019098,0.0003734927,0.0006038826,0.0007641969,0.0008305348,0.0005505825],"category_scores_gemma":[0.009592023,0.0002892273,0.0005225579,0.0004354167,0.001077221,0.001405826,0.001202977,0.001329709,0.0001456777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001693203,"about_ca_system_score_gemma":0.0006557798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004596684,"about_ca_topic_score_gemma":0.004173747,"domain_scores_codex":[0.9987179,0.0003962082,0.00006779344,0.0001832849,0.0004232761,0.0002115851],"domain_scores_gemma":[0.994725,0.00339333,0.000664848,0.0005121008,0.0005128974,0.0001917187],"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":[0.000269166,0.0001206402,0.005442418,0.0000498528,0.00005919647,0.000100593,0.00004286054,0.9516795,0.00223149,0.002567826,0.001255569,0.036181],"study_design_scores_gemma":[0.000001447407,0.00002139087,0.000389304,0.000003472215,0.000002638591,0.0000103614,0.000005833762,0.9978271,0.0008496684,0.0008189147,0.00006770907,0.000002173487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7831351,0.001398046,0.206362,0.001682388,0.0001873297,0.0001110161,0.0003774441,0.001336882,0.005409677],"genre_scores_gemma":[0.9872755,0.0001646822,0.0113608,0.0001422971,0.00002408542,0.00002346895,0.0002409619,0.00002866944,0.0007394542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004596684,"threshold_uncertainty_score":0.01557714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03224449575092127,"score_gpt":0.1992845914996627,"score_spread":0.1670400957487414,"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."}}