DDoS: DeepDefence and Machine Learning for identifying attacks

Abstract

Distributed Denial of Service (DDoS) attacks are very common type of computer attack in the world of internet today. Automatically detecting such type of DDoS attack packets & dropping them before passing through the network is the best prevention method. Conventional solution only monitors and provide the feedforward solution instead of the feedback machine-based learning. A Design of Deep neural network has been suggested in this work and developments have been made on proactive detection of attacks. In this approach, high level features are extracted for representation and inference of the dataset. Experiment has been conducted based on the ISCX dataset published in year 2017,2018 and CICDDoS2019 and program has been developed in Matlab R17b, utilizing Wireshark for features extraction from the datasets. Network Intrusion attacks on critical oil and gas industrial installation become common nowadays, which in turn bring down the giant industrial sites to standstill and suffer financial impacts. This has made the production companies to started investing millions of dollars revenue to protect their critical infrastructure with such attacks with the active and passive solutions available. Our thesis constitutes a contribution to such domain, focusing mainly on security of industrial network, impersonation and attacking with DDoS.