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