Abstract: Internet security is under serious threat due to Distributed Denial of Service (DDoS) attacks. These attacks inflict considerable damage by disrupting network services, resulting in the impairment and complete disablement of system functions. The accurate classification and detection of DDoS attacks is extremely important. We provide a review of different models of Machine Learning (ML)/Deep Learning (DL)-based DDoS attack detection used by researchers that consider different classifiers. Our analysis indicates a heightened emphasis on ML-based classifiers where 22% of studies opted for the widely recognized SVM classifier. For DL-based, 27% of the studies opted for the widely recognized CNN. While the majority of researchers have formulated their datasets, NSL-KDD was employed in 55% of the studies. In addition, we discussed the future directions and challenges of DDoS detection.

Haya Malooh Alqahtani and Monir Abdullah, “A Review on DDoS Attacks Classifying and Detection by ML/DL Models” International Journal of Advanced Computer Science and Applications(IJACSA), 15(2), 2024. http://dx.doi.org/10.14569/IJACSA.2024.0150283

@article{Alqahtani2024,
title = {A Review on DDoS Attacks Classifying and Detection by ML/DL Models},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2024.0150283},
url = {http://dx.doi.org/10.14569/IJACSA.2024.0150283},
year = {2024},
publisher = {The Science and Information Organization},
volume = {15},
number = {2},
author = {Haya Malooh Alqahtani and Monir Abdullah}
}