Machine learning techniques for identifying DDOS attacks in cloud computing background

In a Denial of Service (DoS) attack, malicious actors aim to disrupt the normal functioning of network infrastructure, preventing legitimate programs from establishing connections. This form of cyberwarfare involves inundating the targeted system with a substantial volume of traffic, depleting its resources, and causing network congestion. Unlike other cyber threats, the objective here is not to compromise sensitive data or infiltrate credential files but to render the victim system inaccessible. The attackers exploit the difficulty of managing an overwhelming volume of data traffic, hindering the successful delivery of packets to their intended destinations. Typically, network connections involve a three-way handshake process. The client initiates the connection by sending a request to the server, which, in turn, allocates capacity within its reservoir connection. In this paper, we have designed a DDoS detection system based on the C.4.5 algorithm, Naïve Bayes, and K-NN classifier to prevent the DDoS threat. This algorithm, combined with signature detection techniques, produces a decision tree to accomplish automatic, effective detection of signature attacks for DDoS flooding attacks. To evaluate the system, we formulated additional machine-learning methodologies related to them to obtain the desired results.