Toward Early and Accurate Network Intrusion Detection Using Graph Embedding

Hu, Xiaoyan; Gao, Wenjie; Cheng, Guang; Li, Ruidong; Zhou, Yuyang; Wu, Hua

doi:10.1109/tifs.2023.3318960

Cited by 10 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the GNN-based model, E-GraphSAGE NIDS [21], a GNN approach that allows capturing both edge features of a graph as well as the topological information for network intrusion detection in IoT networks. Hu et al [22] propose a graph embedding method to model the packet interactions in network traffic for NIDS.…”

Section: Deep Learning-based Nids Models and Formatsmentioning

confidence: 99%

Learn-IDS: Bridging Gaps between Datasets and Learning-Based Network Intrusion Detection

Wang,

Yang,

Guo

et al. 2024

Electronics

View full text Add to dashboard Cite

In an era marked by the escalating architectural complexity of the Internet, network intrusion detection stands as a pivotal element in cybersecurity. This paper introduces Learn-IDS, an innovative framework crafted to bridge existing gaps between datasets and the training process within deep learning (DL) models for Network Intrusion Detection Systems (NIDS). To elevate conventional DL-based NIDS methods, which are frequently challenged by the evolving cyber threat landscape and exhibit limited generalizability across various environments, Learn-IDS works as a potent and adaptable platform and effectively tackles the challenges associated with datasets used in deep learning model training. Learn-IDS takes advantage of the raw data to address three challenges of existing published datasets, which are (1) the provided tabular format is not suitable for the diversity of DL models; (2) the fixed traffic instances are not suitable for the dynamic network scenarios; (3) the isolated published datasets cannot meet the cross-dataset requirement of DL-based NIDS studies. The data processing results illustrate that the proposed framework can correctly process and label the raw data with an average of 90% accuracy across three published datasets. To demonstrate how to use Learn-IDS for a DL-based NIDS study, we present two simple case studies. The case study on cross-dataset sampling function reports an average of 30.3% OOD accuracy improvement. The case study on data formatting function shows that introducing temporal information can enhance the detection accuracy by 4.1%.The experimental results illustrate that the proposed framework, through the synergistic fusion of datasets and DL models, not only enhances detection precision but also dynamically adapts to emerging threats within complex scenarios.

show abstract

Section: Deep Learning-based Nids Models and Formatsmentioning

confidence: 99%