{"id":"W4416248540","doi":"10.48550/arxiv.2510.19761","title":"Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adversarial system; Robustness (evolution); Artificial neural network; Deep neural networks; Intrusion detection system; Intrusion","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003488853,0.0009287949,0.0004945146,0.0006264571,0.0004310056,0.0009310783,0.0008233018,0.001068583,0.001583401],"category_scores_gemma":[0.02345342,0.0003816296,0.0003599329,0.0002815859,0.001381809,0.002845905,0.001889288,0.001618939,0.0002392416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001084737,"about_ca_system_score_gemma":0.0005802706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001804368,"about_ca_topic_score_gemma":0.001935433,"domain_scores_codex":[0.9983819,0.0006911951,0.00008603076,0.0002282554,0.0003661539,0.0002465021],"domain_scores_gemma":[0.9827554,0.01302315,0.001424335,0.001517092,0.0008759686,0.000404153],"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":[0.000671552,0.0001604105,0.005073767,0.0001289273,0.0001040105,0.0001343067,0.00007993178,0.9383052,0.0127125,0.005971424,0.0009352001,0.03572287],"study_design_scores_gemma":[0.00001820576,0.0003377679,0.001148851,0.00002330169,0.00002578569,0.00006993252,0.00003913043,0.9808435,0.01160469,0.005526096,0.000348928,0.00001383585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8685824,0.001665505,0.1196854,0.001469784,0.0001504495,0.00009443804,0.0002551269,0.0007377599,0.007359203],"genre_scores_gemma":[0.9915085,0.0001752661,0.00770594,0.00009410763,0.00001373438,0.00001151095,0.0000596563,0.00002886538,0.0004024085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003488853,"threshold_uncertainty_score":0.01845104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06254933044981503,"score_gpt":0.2916652576149747,"score_spread":0.2291159271651597,"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."}}