Detecting DDoS Attacks in Cloud Computing Using Extreme Learning Machine and Adaptive Differential Evolution

Distributed denial of service (DDoS) attacks disrupt the availability of cloud services. The detection of these attacks is a major challenge in the cloud computing environment. Machine learning models can be used to detect these attacks efficiently. In this work, a hybrid machine learning model based approach to detect these attacks is proposed. Firstly, a hybrid machine learning model using extreme learning machine (ELM) and adaptive differential evolution is proposed. In the proposed model, input to hidden layer link weights, and hidden layer biases of ELM are optimized using adaptive differential evolution while weights of links between hidden and output layers are analytically determined. The adaptive differential evolution is modified to choose the apt crossover operator during the evolution process. After that, a DDoS attack detection system using the suggested hybrid model is proposed for cloud computing.. Three state-of-the-art datasets NSL-KDD, ISCX IDS 2012, and CIDDS-001 are used to evaluate the performance of the proposed attack detection system.

Automated summary

In this paper, a hybrid machine learning model based approach is proposed to detect DDoS attacks in cloud computing. The model utilizes extreme learning machine and adaptive differential evolution to optimize the weights, and analytically determines the connection weights. The performance of the system is evaluated using three state-of-the-art datasets.