DOI: 10.11648/j.ajnc.20261502.11 ISSN: 2326-8964

Cross-domain Network Intrusion Detection Based on 1-D CNN, PCA, and GloVe Embedding

Gabriel Iwasokun, Ahmed Ojodu, Johnson Adeyiga, Oludare Olaleye, Mojisola Ogunseye, Ibraheem Jimoh, David Adewole
Show PDF Cite
The existing communication networks are currently encompassed with various malicious activities that aim to compromise the confidentiality, integrity, and availability of data and systems. The activities include malware, phishing, ransomware, Distributed Denial of Service (DDoS) attacks, and insider attacks. The rapid evolution of these threats necessitates the development of advanced and adaptable intrusion detection systems (IDS) capable of operating across diverse network environments. This paper presents the design of a cross-domain network intrusion detection system that leverages a convolutional neural network and principal components analysis to enhance network intrusion detection accuracy and generalisation. The design integrates GloVe (Global Vectors for Word Representation) embeddings to transform network traffic data into a meaningful feature space, utilises Principal Component Analysis (PCA) for dimensionality reduction, and employs a one-dimensional Convolutional Neural Network (1D-CNN) for efficient classification of network activities. The design also considered preprocessing of multiple intrusion detection data from various network domains, and each data is subjected to GloVe-based feature extraction to generate dense vector representations, which are subsequently concatenated to form a unified embedding layer. The PCA component is required for mitigating the issues with dimensionality and enhancing computational efficiency. It will also be used to extract some significant features before the 1D-CNN-enabled intrusion classification. The experimental study of the system established its practical function and suitability for a very high, accurate, and reliable detection of intrusions in multi-domain networks.

More from our Archive