A fuzzy-based ensemble model for improving malicious web domain identification

作者：

Highlights：

• We aim to identify malicious web domains from benign ones using machine learning.

• An improved fuzzy-based ensemble model is proposed for this purpose.

• Real-world web domain data is used to validate and test the proposed model.

• Results show excellent performance of the fuzzy-based ensemble model.

• The model performance can be further enhanced via re-sampling of the data.

摘要

•We aim to identify malicious web domains from benign ones using machine learning.•An improved fuzzy-based ensemble model is proposed for this purpose.•Real-world web domain data is used to validate and test the proposed model.•Results show excellent performance of the fuzzy-based ensemble model.•The model performance can be further enhanced via re-sampling of the data.

论文关键词：Malicious web domain identification,Machine learning,Ensemble models,Least-squares support vector machines,Fuzzy weights,Re-sampling

论文评审过程：Received 6 June 2020, Revised 6 April 2022, Accepted 11 April 2022, Available online 21 April 2022, Version of Record 24 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117243