PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
December 2, 2025Algorithms7 citationsOpen Access

A Deterministic Comparison of Classical Machine Learning and Hybrid Deep Representation Models for Intrusion Detection on NSL-KDD and CICIDS2017

View Full Paper
RBRodolfo Bojorque

Key Points

  • Logistic Regression and hybrid models enhanced detection accuracy on intrusion detection datasets.
  • The best AUC of approximately 0.904 was achieved using Autoencoder embeddings combined with Logistic Regression.
  • Using synthetic minority oversampling techniques provided modest improvements in model performance.
  • These findings highlight the effectiveness of interpretable models in operational intrusion detection systems.

Abstract

Intrusion detection systems (IDSs) must balance detection quality with operational transparency. We present a deterministic, leakage-free comparison of three classical classifiers: Naïve Bayes (NB), Logistic Regression (LR), and Linear Discriminant Analysis (LDA). We also propose a hybrid pipeline that trains LR on Autoencoder embeddings (AE). Experiments use NSL-KDD and CICIDS2017 under two regimes (with/without SMOTE (Synthetic Minority Oversampling Technique) applied only on training data). All preprocessing (one-hot encoding, scaling, and imputation) is fitted on the training split; fixed seeds and deterministic TensorFlow settings ensure exact reproducibility. We report a complete metric set—Accuracy, Precision, Recall, F1, Area Under the Curve (AUC), and False Alarm Rate (FAR)—and release a replication package (code, preprocessing artifacts, and saved prediction scores) to regenerate all reported tables and metrics. On NSL-KDD, AE+LR yields the highest AUC (≈0.904) and the strongest F1 among the evaluated models (e.g., 0.7583 with SMOTE), while LDA slightly edges LR on Accuracy/F1. NB attains very high Precision (≈0.98) but low Recall (≈0.24), resulting in the weakest F1, yet a low FAR due to conservative decisions. On CICIDS2017, LR delivers the best Accuracy/F1 (0.9878/0.9752 without SMOTE), with AE+LR close behind; both approach ceiling AUC (≈0.996). SMOTE provides modest gains on NSL-KDD and limited benefits on CICIDS2017. Overall, LR/LDA remain strong, interpretable baselines, while AE+LR improves separability (AUC) without sacrificing a simple, auditable decision layer for practical IDS deployment.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Rodolfo Bojorque (2025) studied this question.

synapsesocial.com/papers/692e3d846c9b3ab28c187511https://doi.org/10.3390/a18120749
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Comparative performance evaluation of machine learning classifiers for multi-class intrusion detection on the NSL-KDD dataset2026
  2. 2Network Intrusion Detection and Classification System: A Supervised Machine Learning Approach2024 · 2 citations
  3. 3Comparing Machine Learning Algorithms for Intrusion Detection Systems2025
  4. 4A Systematic Analysis and Review on Intrusion Detection Systems Using Machine Learning and Deep Learning Algorithms2024 · 2 citations
  5. 5A Generalized and Robust Nonlinear Approach based on Machine Learning for Intrusion Detection2024