Extracting Optimal Number of Features for Machine Learning Models in Multilayer IoT Attacks
2024

Detecting Multilayer IoT Attacks with Machine Learning

publication 10 minutes Evidence: high

Author Information

Author(s): Sukhni Badeea Al, Manna Soumya K., Dave Jugal M., Zhang Leishi

Primary Institution: Canterbury Christ Church University

Hypothesis

This research aims to develop a Semi-Automated Intrusion Detection System (SAIDS) that integrates efficient feature selection and human expertise to detect multilayer attacks in IoT systems.

Conclusion

The proposed SAIDS framework effectively identifies multilayer attacks using an optimal set of 13 significant features, achieving over 94% accuracy with the KNN model.

Supporting Evidence

  • The KNN algorithm demonstrated an average accuracy exceeding 94% in detecting multilayer attacks.
  • The proposed framework extracted an optimal set of 13 significant features out of 64 in the Edge-IIoT dataset.
  • Existing research on multilayer IoT attacks exhibits gaps in real-world applicability.

Takeaway

This study created a smart system that helps find bad guys trying to attack our internet-connected devices by picking out the most important clues.

Methodology

The study used a semi-automated approach combining feature selection, feature weighting, and human expertise to improve detection accuracy.

Potential Biases

The reliance on automated processes without human input in feature selection may affect the reliability of detection models.

Limitations

Some models, like Naive Bayes, struggled with complex attack types such as XSS, indicating a need for more advanced methodologies.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.3390/s24248121

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication