Distributed code behavior vulnerability with nano science fuzzy scanning algorithm based on machine learning

In view of the fact that the distributed code behavior vulnerability fuzzy scanning algorithm does not consider the vulnerability feature selection method, which leads to the low accuracy and long scanning time of distributed code behavior vulnerability fuzzy scanning. A distributed code behavior vulnerability fuzzy scanning algorithm based on machine learning is proposed. According to the characteristics of kernel principal component analysis, this paper compares the effects of different kernel functions, obtains the vulnerability feature selection method and kernel function, finds the most suitable feature mapping, and transforms it into a feature sample set. In depth study of vulnerability scanning technology, combined with the characteristics of P2P network structure and vulnerability scanning, the distributed code behavior vulnerability fuzzy scanning model is constructed. Each scanning node cooperates with each other to complete the scanning task issued by the user, and the node join and exit mechanism are designed to seek the optimal scheduling matrix of the scanning task set, complete the vulnerability scanning task scheduling, and realize the distributed code line fuzzy scan for vulnerabilities. Experimental results show that the proposed algorithm has high accuracy and can effectively shorten the vulnerability scanning time.