The economic impact of (distributed) denial-of-service attacks is substantial, especially at a time when we rely on web applications more and more often. That is why, it is essential to be able to detect such threats early and therefore react before significant financial losses. In this paper, we focus on techniques, for detecting this type of attacks, that use historical data. We will discuss existing datasets, extracted features and finally the methods themselves. The solutions mentioned in this work are based on supervised learning (k-NN, MLP, DNN), unsupervised learning (mostly modified K-Means) and anomaly detection in time series analysis (ARIMA models family).
CITATION STYLE
Gniewkowski, M. (2020). An Overview of DoS and DDoS Attack Detection Techniques. In Advances in Intelligent Systems and Computing (Vol. 1173 AISC, pp. 233–241). Springer. https://doi.org/10.1007/978-3-030-48256-5_23
Mendeley helps you to discover research relevant for your work.