Research On XSS Detection Method Based On Improved GA

The past few years have seen the unprecedentedly rapid emergence of the XSS attack technology and this technology seriously affect the safety of computer network in the world with the rapid development of Internet technology which promote social progress. Some of the more common security technologies are Firewalls, IDS, router filtering, system audit, hole digging and so on. It can be divided into two kinds of protection technology: static protection technology and dynamic protection technology. Because of the constantly updated of the network intrusion methods, a single static protection technology is hard to continue to protect networks from attack, even the protective tool itself will also be threatened.Therefore, the study on the cross site scripting attack dynamic defense technology is imminent.Instruction detection system(IDS) is a dynamic secure technology. It is the important approach for effective cyber security assurance as the second line of defense for computer and network systems. Aim at the problem of most intrusion detection systems: such as high false positive rate and inefficiency. Here, this paper mainly research on the follow aspects: the design of detection model, improved Genetic Algorithm trains the Neural Network and so on. We introduced the background and development of the detection of XSS technology and the fundamentals of neural networks and GA. And we also summarized the advantages and disadvantages of the genetic algorithm in the aspect of operators.This paper designed a detect systerm based on improved Genetic Algorithm for XSS,studied the core coment of the systerm,the detector of fuzzing, thus improving the detecting efficiency of cross site scripting,designed the implementation of the systerm.This design combines simulated annealing method and the improved genetic algorithm to strengthen the local search ability of genetic algorithm. In order to improve the diversity and effectiveness of the test cases for detecting the XSS,thispaper uses a method of an improved Genetic Algorithm,The experimental study shows that improved Genetic Algorithm training the Neural Network could optimize the generation of test cases, so it improves the efficiency and decrease mistake warning rate.This paperintended to apply the improved genetic algorithm optimizing neural network into the detection of XSS technology. Having abandoned conventional detection methodology and adoptting more advanced brain-like nonlinear neural network technology.It has very important theoretic and practical significance for the detection of XSS.