Analysis of XSS attack based on ensemble learning
Ruiheng Liu, Boyao You, Jin Chang-Qing, Chengying Zhu, Wenlong Wang, Haolin Jin · 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering · 2022
In this paper, we collected real XSS attack logs from web servers for the problem of XSS attack defense in real environment. Relevant features were selected and a low memory consumption XSS matching filtering model was constructed using the Random Forest algorithm. By comparing with traditional machine learning and other integrated algorithms, it is found that Random Forest is faster to train and consumes less memory during training while ensuring accuracy. The experimental results show that the model has better classification results and is more suitable for deployment on browser clients.