Unsafe XSS defense system identification method based on reinforcement learning

Abstract

The invention provides an unsafe cross-website script (XSS) defense system identification method based on reinforcement learning. The method comprises the following steps of carrying out feature extraction on an XSS attack load; defining a killing-free operation; using whether the XSS defense system is safe or not as a basis for judging whether the XSS defense system is an XSS attack load or not;constructing a reinforcement learning environment; realizing the reinforcement learning of a DQN algorithm through a DQNAgent object; and completing the model training, and judging whether the XSS defense system is safe or not. When all the undeformed XSS attack load samples are deformed, if the load which bypasses the XSS defense system is not successful, the XSS defense system is indicated to besafe, otherwise, the XSS defense system is indicated to be unsafe, at the same time, a deformation model is obtained, and the load which bypasses the XSS defense system can be generated by utilizingthe model. According to the invention, the defense capability of the XSS defense system is enhanced, the current network environment security is further improved, and meanwhile, the loss caused by carelessness of the XSS defense system due to the adoption of a certain defense measure can be avoided.

Description

technical field [0001] The invention relates to the technical field of network security, in particular to an identification method of an insecure XSS defense system based on reinforcement learning. Background technique [0002] While the Internet provides convenience and speed to the public, it also exposes more and more serious problems, some of which have brought huge network security risks. One of the most prominent is the problem of Web application security. Due to the wide application of Web application services, many hackers focus their attacks on Web applications and their background data, and XSS vulnerability is a common and extremely harmful vulnerability in the "Web 2.0" period. [0003] XSS vulnerabilities pose a great threat to web security. Using XSS vulnerabilities can steal cookies, hijack sessions, and launch phishing attacks. Many large platforms at home and abroad have suffered XSS attacks. In June 2011, more than 30,000 users of Sina Weibo, a large soc...

AI Technical Summary

Problems solved by technology

However, the XSS attack methods are varied, even if the XSS defense system is used, there is a possibility of being bypassed, and the attack is successful

Images