Next Article in Journal
Artificial Intelligence Imagery Analysis Fostering Big Data Analytics
Previous Article in Journal
Research on Factors Affecting Solvers’ Participation Time in Online Crowdsourcing Contests
Open AccessArticle

RLXSS: Optimizing XSS Detection Model to Defend Against Adversarial Attacks Based on Reinforcement Learning

by 1, 1,*, 1 and 2
1
College of Cybersecurity, Sichuan University, Chengdu 610065, Sichuan, China
2
College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, Sichuan, China
*
Author to whom correspondence should be addressed.
Future Internet 2019, 11(8), 177; https://doi.org/10.3390/fi11080177
Received: 18 July 2019 / Revised: 10 August 2019 / Accepted: 12 August 2019 / Published: 14 August 2019
(This article belongs to the Section Cybersecurity)
With the development of artificial intelligence, machine learning algorithms and deep learning algorithms are widely applied to attack detection models. Adversarial attacks against artificial intelligence models become inevitable problems when there is a lack of research on the cross-site scripting (XSS) attack detection model for defense against attacks. It is extremely important to design a method that can effectively improve the detection model against attack. In this paper, we present a method based on reinforcement learning (called RLXSS), which aims to optimize the XSS detection model to defend against adversarial attacks. First, the adversarial samples of the detection model are mined by the adversarial attack model based on reinforcement learning. Secondly, the detection model and the adversarial model are alternately trained. After each round, the newly-excavated adversarial samples are marked as a malicious sample and are used to retrain the detection model. Experimental results show that the proposed RLXSS model can successfully mine adversarial samples that escape black-box and white-box detection and retain aggressive features. What is more, by alternately training the detection model and the confrontation attack model, the escape rate of the detection model is continuously reduced, which indicates that the model can improve the ability of the detection model to defend against attacks. View Full-Text
Keywords: reinforcement learning; cross-site scripting; adversarial attacks; double deep Q network reinforcement learning; cross-site scripting; adversarial attacks; double deep Q network
Show Figures

Graphical abstract

MDPI and ACS Style

Fang, Y.; Huang, C.; Xu, Y.; Li, Y. RLXSS: Optimizing XSS Detection Model to Defend Against Adversarial Attacks Based on Reinforcement Learning. Future Internet 2019, 11, 177.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop