Cascaded Multi-Class Network Intrusion Detection With Decision Tree and Self-attentive Model

Page view(s)
34
Checked on Feb 23, 2025
Cascaded Multi-Class Network Intrusion Detection With Decision Tree and Self-attentive Model
Title:
Cascaded Multi-Class Network Intrusion Detection With Decision Tree and Self-attentive Model
Journal Title:
2022 IEEE International Conference on Data Mining Workshops (ICDMW)
Keywords:
Publication Date:
08 February 2023
Citation:
Lan, Y., Truong-Huu, T., Wu, J., & Teo, S. G. (2022). Cascaded Multi-Class Network Intrusion Detection With Decision Tree and Self-attentive Model. 2022 IEEE International Conference on Data Mining Workshops (ICDMW). https://doi.org/10.1109/icdmw58026.2022.00081
Abstract:
Network intrusion has become a leading threat to breaching the security of Internet applications. Deep neural networks (DNN) have been widely used for network intrusion detection. However, one main problem with the DNN models is the dependency on sufficient training data to achieve decent accuracy. DNN models may incur many false predictions on the imbalanced intrusion dataset on the minority classes. This paper considers the problem of network intrusion detection with a machine learning algorithm, which effectively integrates the decision tree and FT (feature tokenizer)-transformer. First, the decision tree algorithm is used for the binary classification of regular (normal) traffic and malicious attacks. Second, FT- transformer performs the multi-category classification on those malicious attack data. We conduct the performance evaluation using the open-source UNSW-NB15 and CIC-IDS 2017 datasets. Evaluation results demonstrates that proposed framework can achieve the macro precision, recall and f1-score with 84.6%, 83.6%, and 93.2%.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
979-8-3503-4609-1
Files uploaded: