Analysis of Machine Learning Classification Techniques for Anomaly Detection with NSL-KDD Data Set

Cholakoska, Ana; Shushlevska, Martina; Todorov, Zdravko; Efnusheva, Danijela

doi:10.1007/978-3-030-90321-3_21

Cited by 6 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In today's landscape, the optimization of processing and training procedures is imperative for constructing models that can effectively safeguard systems against dubious and spyware activities [12]. However, it's worth noting that many contemporary ML-IDS solutions tend to be limited by their reliance on small, outdated and balanced datasets for model development [17][18][19]. The focus on these smaller, often outdated datasets, coupled with imbalances in the data distribution, while facilitating preprocessing and training with diverse ML algorithms, raises questions regarding the practical applicability of these models in real-world scenarios, specifically when dealing with big data.…”

mentioning

confidence: 99%

Machine learning-based network intrusion detection for big and imbalanced data using oversampling, stacking feature embedding and feature extraction

Talukder,

Islam,

Uddin

et al. 2024

J Big Data

View full text Add to dashboard Cite

Cybersecurity has emerged as a critical global concern. Intrusion Detection Systems (IDS) play a critical role in protecting interconnected networks by detecting malicious actors and activities. Machine Learning (ML)-based behavior analysis within the IDS has considerable potential for detecting dynamic cyber threats, identifying abnormalities, and identifying malicious conduct within the network. However, as the number of data grows, dimension reduction becomes an increasingly difficult task when training ML models. Addressing this, our paper introduces a novel ML-based network intrusion detection model that uses Random Oversampling (RO) to address data imbalance and Stacking Feature Embedding based on clustering results, as well as Principal Component Analysis (PCA) for dimension reduction and is specifically designed for large and imbalanced datasets. This model’s performance is carefully evaluated using three cutting-edge benchmark datasets: UNSW-NB15, CIC-IDS-2017, and CIC-IDS-2018. On the UNSW-NB15 dataset, our trials show that the RF and ET models achieve accuracy rates of 99.59% and 99.95%, respectively. Furthermore, using the CIC-IDS2017 dataset, DT, RF, and ET models reach 99.99% accuracy, while DT and RF models obtain 99.94% accuracy on CIC-IDS2018. These performance results continuously outperform the state-of-art, indicating significant progress in the field of network intrusion detection. This achievement demonstrates the efficacy of the suggested methodology, which can be used practically to accurately monitor and identify network traffic intrusions, thereby blocking possible threats.

show abstract

mentioning

confidence: 99%