A Deep Learning-Based Methodology in Fog Environment for DDOS Attack Detection

The Distributed denial-of-service (DDoS) attack pose a great threat to a heterogeneous network like Internet of things (IoT). The loss to a firm caused by a DDoS attack is directly proportional to the duration of the attack so it is important to identify and mitigate the attack as soon as possible. The traditional architecture of IoT has three layers consisting of the end device in the bottommost layer, controllers in the middle layer, and cloud in the uppermost layer. Any kind of decision-making is done in the cloud so the whole process is slowed down due to latency delay. We have adopted the architecture of a fog layer with sufficient computing power above the end device layer. We have used two deep Learning-based models. First long short-term memory (LSTM) model to identify the malicious data from the benign data and second convolutional neural network (CNN) model to further classify the data into attack categories. Our lstm model has an accuracy of 98 percent and cnn model has an accuracy of 86 percent.