A New Web Service Protection Model

With the rapid development of the Internet,the number of important industry websites has been increasing.The Web service of these websites face multiple security threats such as the page being tampered with,and being attacked.The characteristics of Web service being attacked in the network environment have become more and more new and large-scale,and new Web protection models are urgently needed.Currently,the tamper-resistant system runs on a single node.The credibility of the node itself cannot be guaranteed,and it faces a single point of failure.This paper proposes a webpage tamper-proof method based on blockchain and trusted computing technology,defines a secure web server model supported by trusted computing technology,and guarantees the credibility of a single node.A blockchain that is more suitable for the system is proposed to solve the trust problem among multiple nodes.A prototype system is designed and implemented.The experiment proves that the problem that the website is attacked and the page is tampered can be effectively solved.At present,the method of detecting Web attacks is mainly rule matching,and it is difficult to efficiently identify Web attack.A Web-based attack detection method based on convolutional neural network is proposed.The Web access traffic is converted into a gray-scale image,that is,a traffic image.For the traditional convolutional neural network can only deal with the limitations of fixed-size input,build a convolutional neural network based on space pyramid pooling,make it suitable for processing different sizes of Web traffic,and identify Web attack from many Web traffic.Experiments show that the method is more efficient and accurate than the rule matching method and the traditional convolutional neural network in identifying Web attack.