@inproceedings{cf2842b7d3c342aaa26c48152393faa3,
title = "Leverage temporal convolutional network for the representation learning of URLs",
abstract = "Cyber crimes including computer virus/malwares, spam, illegal sales, and phishing websites are proliferated aggressively via the disguised Uniform Resource Locators (URL). Although numerous studies were conducted for the URL classification task, the traditional URL classification solutions retreated due to the hand-crafted feature engineering and the boom of newly generated URLs. In this paper, we study the representation learning of URLs, and explore the URL classification using deep learning. Specifically, we propose URL2vec to extract both the structural and lexical features of URLs, and apply temporal convolutional network (TCN) for the URL classification task. The experimental results show that URL2vec outperforms both word2vec and character-level embedding for URL representation, and TCN achieves the best performance than baselines with the precision up to 95.97%.",
keywords = "Cyber Crime, Temporal Convolutional Network, URL Classification, URL2vec",
author = "Yunji Liang and Jian Kang and Zhiwen Yu and Bin Guo and Xiaolong Zheng and Saike He",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019 ; Conference date: 01-07-2019 Through 03-07-2019",
year = "2019",
month = jul,
doi = "10.1109/ISI.2019.8823362",
language = "英语",
series = "2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "74--79",
editor = "Xiaolong Zheng and Ahmed Abbasi and Michael Chau and Alan Wang and Lina Zhou",
booktitle = "2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019",
}
