Detection and Defense of XSS Attack Script Based on Machine Learning

With the rapid development of the Internet, many things of people can be done online, and the Internet has been integrated into people's daily life. Web applications widely used in all walks of life are convenient for people to use, but also bring some security problems. Cross-Site Scripting(XSS) vulnerability detection method based on dynamic analysis is an effective XSS vulnerability detection method, which simulates real attack behavior to conduct penetration test on Web applications. However, there are still some problems such as low detection coverage, low detection efficiency and low detection accuracy. Based on this, this paper expounds the research status and background of XSS attack detection, puts forward the necessity of using machine learning algorithm for XSS attack detection, applies SVM algorithm to XSS detection, analyzes and extracts the features of XSS samples, selects radial basis kernel function for nonlinear SVM training, and verifies the generated detection model. It is found that the SVM model in this paper is also superior to the comparison algorithm in accuracy and false alarm rate.