2025 IEEE International Conference on Cyber Security and Resilience

Full Program

Summary:

The rapid expansion of Internet of Things (IoT) systems has expanded the threat surface as well as the increased likelihood of cyber-attacks that can result in Denial-of-Service (DoS) in the system operation. Prominent attacks leading to DoS belong to the blackhole flooding sinkhole and spoofing categories. The detection of these attacks though still remains a great challenge which necessitates the presence of more accurate and robust detection methods. To this end in this paper we investigate the use of Machine Learning (ML) models to perform cross-layer detection and compare them with single-layer detection approaches across several IoT systems. In our analysis we evaluate performance metrics (accuracy precision recall F1-score) across all attacks. Results reveal that cross-layer methodologies consistently outperform single-layer detection achieving higher accuracy and almost all cases lower variability. Additionally feature selection is another advantage of cross-layer methodologies with multi-layered datasets enabling more robust detection compared to single-layer approaches.

Author(s):

Dimitrios Tasiopoulos    
University of Thessaly
Greece

Apostolis Xenakis    
University of Thessaly
Greece

Alexios Lekidis    
University of Thessaly
Greece

Dimitrios Kosmanos    
Greece

Costas Chaikalis    
University of Thessaly
Greece

Vasileios Vlachos    
University of Thessaly
Greece

 


Copyright © 2025 SUMMIT-TEC GROUP LTD