Multi-scale semantic deep fusion models for phishing website detection

作者：

Highlights：

• Semantic information at different scales is mined and fused at different depths.

• Three semantic-based deep phishing detection models are proposed.

• Various comparative experiments are carried out and prove the effectiveness.

• A phishing discovery experiment in reality detected 3016 phishing websites.

摘要

•Semantic information at different scales is mined and fused at different depths.•Three semantic-based deep phishing detection models are proposed.•Various comparative experiments are carried out and prove the effectiveness.•A phishing discovery experiment in reality detected 3016 phishing websites.

论文关键词：Deep learning,Semantic deep fusion,Phishing detection

论文评审过程：Received 23 May 2022, Revised 18 July 2022, Accepted 25 July 2022, Available online 1 August 2022, Version of Record 9 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118305