Detection and Mitigation of DDOS Attack Using Deep Learning

Attacks known as distributed denial of service (DDoS) are becoming more and more dangerous for organisations and governments. They hurt company branding, restrict access to information and services, and hurt online companies. Because they mimic real users, attackers deploy application layer DDoS attacks, which are difficult to identify. We analyse incoming packet characteristics such as the size of HTTP frame packets, the number of conveyed Internet Protocol (IP) addresses, the number of constant port mappings, and the number of IP addresses employing proxy IP in order to combat unique application layer DDoS attacks in this work. Using standard datasets, the CTU-13 dataset, real weblogs (dataset) from our organisation, and experimentally constructed datasets from DDoS attack tools, we examined client behaviour in public attacks. Metrics-based attack detection is assessed using a deep learning method called a multilayer perceptron (MLP). The suggested MLP classification system has a 98.99% detection efficiency for DDoS attacks, according to simulation findings. When compared to traditional classifiers, our suggested technique’s performance yielded the lowest proportion of false positives—2.11%.