Denial-of-service (DoS) attacks develop unauthorized entry to various network services and user information by building traffic that creates multiple requests simultaneously making the system unavailable to users. Protection of internet services requires effective DoS attack detection to keep an eye on traffic passing across protected networks, freeing the protected internet servers from surveillance threats and ensuring they can focus on offering high-quality services with the fewest response times possible.
This paper aims to develop a hybrid optimization-based deep learning model to precisely detect DoS attacks.
The designed Aquila deer hunting optimization-enabled deep belief network technique achieved improved performance with an accuracy of 92.8%, a true positive rate of 92.8% and a true negative rate of 93.6.
The introduced detection approach effectively detects DoS attacks available on the internet.
