LRDADF: An AI Enabled Framework for Detecting Low-Rate DDoS Attacks in Cloud Computing Environments

Abstract

In cloud computing environment DDoS attacks are continually evolving with intelligent strategies. Low-rate DDoS attack is one such strategy that make it difficult to detect attack. At the same time, cloud infrastructure is also evolving rapidly. Container based technology enables cloud computing to have lightweight approaches in resource utilization and flexibility in scaling services. The existing DDoS attack detection methods used in cloud computing are not adequate when adversaries employ the modality known low-rate DDoS attack. There is need for an approach that not only detects the attack but also defeat the attack as much as possible. Towards this end, in this paper, we proposed a framework named Low-Rate DDoS Attack Detection Framework (LRDADF). Since low-rate DDoS attacks are difficult to be defeated, we proposed a mathematical model to realize mitigation strategy besides employing deep learning methods to have effective means of detecting such attacks. We proposed an algorithm named Hybrid Approach for Low-Rate DDoS Detection (HA-LRDD). The algorithm uses an Artificial Intelligence (AI) enabled methods comprising of deep Convolutional Neural Network (CNN) and deep autoencoder. Another algorithm known as Dynamic Low-Rate DDoS Mitigation (DLDM) is used to minimize the effect of the attack after detection or even defeat the attack by ensuring the smooth functioning of cloud infrastructure which is under attack. Extensive simulation study revealed that the proposed framework is able to detect low-rate DDoS attacks and also mitigate the attacks to ensure there is acceptable quality of service in cloud computing environments.