A User Behavior Analytics (UBA)- based solution using LSTM Neural Network to mitigate DDoS Attack in Fog and Cloud Environment

Distributed denial of service (DDoS) cyber-attack poses a severe threat to the industrial Internet of Things (IIoT) operation due to the security vulnerabilities resulted from increased connectivity and openness, and the large number of deployed low computation power devices. The aim of this paper is to provide a solution to the application-level DDoS attack, which is increasingly difficult to detect because botnets tend to get confused with various legitimate users. The proposed solution aims to study the behavior of users and bots, through a User Behavior Analytics (UBA) solution by using Long Short-Term Memory (LSTM) neural networks to provide a potentially ideal solution to mitigate this type of attack. Accuracy, precision and recall were used to evaluate the model. The values of the three metrics resulting from the training of the model are all very high, which makes us understand that the model reacts well to illicit users but at the same time it does not exchange the licit users for malicious ones.