Detection Systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review

Abstract

The Distributed Denial-of-Service (DDoS)attacks are one of the most critical threats to the stability andsecurity of the Internet. With the increasing number of devicesconnected to the Internet, the frequency and severity of DDoSattacks are also increasing. To mitigate the impact of DDoSattacks, intelligent detection systems are becoming increasinglyimportant. This paper reviews the recent literature onintelligent techniques, including machine learning (ML), DeepLearning (DL), and artificial intelligence (AI), for detectingDDoS attacks. We will provide an overview of the existingresearch in the field and analyse the trends in using time seriesdata analysis for DDoS attack detection. A taxonomy andconceptual framework for DDoS mitigation are presented. Thisstudy highlights the use of several intelligent techniques fordetecting DDoS attacks and evaluates the performance utilizingreal datasets and also discusses future research directions in thisfield.

(PDF) Detection Systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review. Available from: https://www.researchgate.net/publication/381378092_Detection_Systems_for_Distributed_Denial-of-Service_DDoS_Attack_Based_on_Time_Series_A_Review [accessed Jan 28 2025].