Detection of distributed denial of service attacks using the Viola-Jones algorithm.
Viola-Jones, DDoS Attack Detection, Machine Learning, Computer Networks
With the expansion of the Internet, combined with the growing number of Internet of Things (IoT) devices, denial of service attacks (Denial of Service - DoS), as well as their distributed variant (Distributed Denial of Service - DDoS) have become making it a problem for the availability of services operating on the Internet. This type of attack is generated when an attacker tries to prevent or interrupt access to a network or service, being used by criminals for numerous purposes, such as hijacking the attacked service, or even as a disguise for other types of attacks aimed at stealing confidential data. Therefore, DDoS attacks have become one of the biggest security problems on the internet. In recent years, the number of researches in academia and industry on the detection and mitigation of these attacks has increased, but without a definitive solution. Techniques involving machine learning are being widely used to detect and mitigate these attacks. Although efficient, the proposed techniques have a high computational cost, which may make them unfeasible in network scenarios with intense data flows, due to the temporal restrictions imposed by the real-time processing of the data flow. Inspired by image processing techniques aimed at detecting faces and objects in real time, this work proposes a new approach to detect DDoS attacks, using the Viola-Jones algorithm. This method is normally used in detection systems due to its high success rate, low false positive rate and its relative simplicity of implementation, with great efficiency in processing large volumes of data, making it suitable for the task of detecting DDoS attacks in network scenarios with high throughputs.