Unsafe XSS defense system identification method based on reinforcement learning

A defense system and reinforcement learning technology, applied in the field of network security, can solve problems such as being bypassed, and achieve the effects of avoiding losses, improving security, and strengthening defense capabilities

Active Publication Date: 2019-10-08
JINAN UNIVERSITY
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Unsafe XSS defense system identification method based on reinforcement learning
  • Unsafe XSS defense system identification method based on reinforcement learning
  • Unsafe XSS defense system identification method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Such as figure 1 As shown, the present invention provides a method for identifying an insecure XSS defense system based on reinforcement learning, comprising the following steps:

[0033] S1. Use the Bytes Histogram method to perform feature extraction on the XSS attack load. The purpose of feature extraction is to vectorize the XSS attack load to extract features, and use the feature vector of the XSS attack load as the state to transfer.

[0034] Convert the XSS attack load string to a byte histogram (Bytes Histogram), and convert the string to a byte array, count the number of occurrences of each character, and add a dimension to indicate the string length, using the defined string length The frequency of occurrence is calculated for all byte occurrences, so as to avoid excessive characters from adversely affecting the model.

[0035] by alert( / 1 / ) As an example, through byte histogram conversion to get such as image 3 The 257-dimensional feature vector shown.

...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/57H04L29/06G06N3/08
CPCG06F21/577G06F2221/033G06N3/08H04L63/1433H04L63/1441
Inventor 魏林锋黎琳宣建通
Owner JINAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap