Cloud computing network intrusion risk detection method under large-scale DDoS attack
Shouhe Qiao · 2022
Aiming at the problems of low sensitivity and poor F value of comprehensive index in traditional detection methods, a cloud computing network intrusion risk detection method based on Naive Bayesian algorithm is proposed to detect the risk under large-scale DDoS attacks. Under DDoS attack, linear chain conditional random field is used to analyze the characteristics of cloud computing network intrusion risk, and a feature selection algorithm based on maximum correlation or minimum redundancy is proposed; The naive Bayesian algorithm is used to reduce the dimension of cloud computing network intrusion risk, and the Bayesian optimal classifier is introduced to realize cloud computing network intrusion risk detection. The experimental results show that when the number of attacks increases, compared with the traditional method, the improved method has high sensitivity and improved comprehensive index, which has certain advantages.