Deep-Learning-Based Approach to Detect ICMPv6 Flooding DDoS Attacks on IPv6 Networks

Internet Protocol version six (IPv6) is more secure than its forerunner, four (IPv4). IPv6 introduces several new protocols, such as the Control Message (ICMPv6), an essential protocol to networks. However, it exposes networks some security threats since ICMPv6 messages are not verified or authenticated, and they mandatory that cannot be blocked disabled. One of currently facing exploitation by malicious actors execute distributed denial service (DDoS) attacks. Therefore, this paper proposes a deep-learning-based approach detect flooding DDoS attacks on introducing ensemble feature selection technique utilizes chi-square information gain ratio methods select significant features for attack detection with high accuracy. In addition, long short-term memory (LSTM) employed train model selected features. The proposed was evaluated using synthetic dataset false-positive rate (FPR), accuracy, F-measure, recall, precision, achieving 0.55%, 98.41%, 98.39%, 97.3%, 99.4%, respectively. Additionally, results reveal outperforms existing approaches.