# TransURL: Improving malicious URL detection with multi-layer Transformer encoding and multi-scale pyramid features

arXiv: https://arxiv.org/abs/2312.00508 · HTML: https://mlsanity.com/paper/2312.00508/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2023.

## Built on by (most cited first, 5 of 5)

- [Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classification](https://mlsanity.com/paper/2402.11495/) (2024)
- [A Novel Approach to Malicious Code Detection Using CNN-BiLSTM and Feature Fusion](https://mlsanity.com/paper/2410.09401/) (2024)
- [From Past to Present: A Survey of Malicious URL Detection Techniques, Datasets and Code Repositories](https://mlsanity.com/paper/2504.16449/) (2025)
- [MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2505.10289/) (2025)
- [WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT](https://mlsanity.com/paper/2506.19356/) (2025)

## Abstract (arXiv)

Machine learning progress is advancing the detection of malicious URLs. However, advanced Transformers applied to URLs face difficulties in extracting local information, character-level details, and structural relationships. To address these challenges, we propose a novel approach for malicious URL detection, named TransURL. This method is implemented by co-training the character-aware Transformer with three feature modules: Multi-Layer Encoding, Multi-Scale Feature Learning, and Spatial Pyramid Attention. This specialized Transformer enables TransURL to extract embeddings with character-level information from URL token sequences, with the three modules aiding the fusion of multi-layer Transformer encodings and the capture of multi-scale local details and structural relationships. The proposed method is evaluated across several challenging scenarios, including class imbalance learning, multi-classification, cross-dataset testing, and adversarial sample attacks. Experimental results demonstrate a significant improvement compared to previous methods. For instance, it achieved a peak F1-score improvement of 40% in class-imbalanced scenarios and surpassed the best baseline by 14.13% in accuracy for adversarial attack scenarios. Additionally, a case study demonstrated that our method accurately identified all 30 active malicious web pages, whereas two previous state-of-the-art methods missed 4 and 7 malicious web pages, respectively. The codes and data are available at: https://github.com/Vul-det/TransURL/.