The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information, and local-global encoding integration. To address these challenges, we propose PMANet, a pre-trained Language Model-Guided multi-level feature attention network. PMANet employs a post-training process with three self-supervised objectives: masked language modeling, noisy language modeling, and domain discrimination, effectively capturing subword and character-level information. It also includes a hierarchical representation module and a dynamic layer-wise attention mechanism for extracting features from low to high levels. Additionally, spatial pyramid pooling integrates local and global features. Experiments on diverse scenarios, including small-scale data, class imbalance, and adversarial attacks, demonstrate PMANet's superiority over state-of-the-art models, achieving a 0.9941 AUC and correctly detecting all 20 malicious URLs in a case study. Code and data are available at https://github.com/Alixyvtte/Malicious-URL-Detection-PMANet.
@article{arxiv.2311.12372,
title = {PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network},
author = {Ruitong Liu and Yanbin Wang and Haitao Xu and Zhan Qin and Fan Zhang and Yiwei Liu and Zheng Cao},
journal= {arXiv preprint arXiv:2311.12372},
year = {2025}
}