What question did this study set out to answer?

This research evaluates the effectiveness of various machine learning and deep learning models for network anomaly detection.

May 8, 2026Open Access

Assessing the strength of machine learning and deep learning models for network anomaly detection: insights from multi-dataset cybersecurity analysis

Key Points

This research evaluates the effectiveness of various machine learning and deep learning models for network anomaly detection.
Evaluated six anomaly detection models: four machine learning (Random Forest, Isolation Forest, Local Outlier Factor, One-Class SVM) and two deep learning (LSTM-CNN, Autoencoder).
Utilized four public datasets (UNSW-NB15, CICIDS-2017, NSL-KDD, ToN-IoT) totaling over five million records.
Analyzed model performance using parallel preprocessing on 16 CPU cores and GPU acceleration.
Achieved a 10.8 times speedup with parallel preprocessing on 16 CPU cores.
Deep learning models reached a 35 times speedup using GPU processing.
Random Forest model demonstrated stable performance with F1 score greater than 0.95.

Abstract

Abstract Network anomaly detection is one of the key aspects to be considered for the protection of modern digital infrastructures against changing cyber-attacks. As networks are becoming increasingly larger and complex, the processing of millions of flows in real time is a high-performance computing (HPC) issue that requires parallel and distributed computing. This paper aims to evaluate the performance of six anomaly detection models: four machine learning models (Random Forest, Isolation Forest, Local Outlier Factor, One-Class SVM) and two deep learning models (LSTM-CNN, Autoencoder). The performance evaluation is done using four public datasets (UNSW-NB15, CICIDS-2017, NSL-KDD, ToN-IoT) with over five million data records. The results showed that parallel preprocessing achieves a 10.8 times speedup on 16 CPU cores, while GPU achieves a 35 times speedup for deep learning models. Among the models, the performance of the Random Forest is found to be stable with F1 > 0.95.

Bookmark

View Full Paper