Leverage temporal convolutional network for the representation learning of URLs

Yunji Liang; Jian Kang; Zhiwen Yu; Bin Guo; Xiaolong Zheng; Saike He

doi:10.1109/ISI.2019.8823362

Leverage temporal convolutional network for the representation learning of URLs

Yunji Liang
, Jian Kang
, Zhiwen Yu
, Bin Guo
, Xiaolong Zheng
, Saike He

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

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%.

Original language	English
Title of host publication	2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019
Editors	Xiaolong Zheng, Ahmed Abbasi, Michael Chau, Alan Wang, Lina Zhou
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	74-79
Number of pages	6
ISBN (Electronic)	9781728125046
DOIs	https://doi.org/10.1109/ISI.2019.8823362
State	Published - Jul 2019
Event	17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019 - Shenzhen, China Duration: 1 Jul 2019 → 3 Jul 2019

Publication series

Name	2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019

Conference

Conference	17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019
Country/Territory	China
City	Shenzhen
Period	1/07/19 → 3/07/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Keywords

Cyber Crime
Temporal Convolutional Network
URL Classification
URL2vec

Access to Document

10.1109/ISI.2019.8823362

Cite this

Liang, Y., Kang, J., Yu, Z., Guo, B., Zheng, X., & He, S. (2019). Leverage temporal convolutional network for the representation learning of URLs. In X. Zheng, A. Abbasi, M. Chau, A. Wang, & L. Zhou (Eds.), 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019 (pp. 74-79). Article 8823362 (2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISI.2019.8823362

Liang, Yunji ; Kang, Jian ; Yu, Zhiwen et al. / Leverage temporal convolutional network for the representation learning of URLs. 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019. editor / Xiaolong Zheng ; Ahmed Abbasi ; Michael Chau ; Alan Wang ; Lina Zhou. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 74-79 (2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019).

@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",

}

Liang, Y, Kang, J, Yu, Z, Guo, B, Zheng, X & He, S 2019, Leverage temporal convolutional network for the representation learning of URLs. in X Zheng, A Abbasi, M Chau, A Wang & L Zhou (eds), 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019., 8823362, 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019, Institute of Electrical and Electronics Engineers Inc., pp. 74-79, 17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019, Shenzhen, China, 1/07/19. https://doi.org/10.1109/ISI.2019.8823362

Leverage temporal convolutional network for the representation learning of URLs. / Liang, Yunji; Kang, Jian; Yu, Zhiwen et al.
2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019. ed. / Xiaolong Zheng; Ahmed Abbasi; Michael Chau; Alan Wang; Lina Zhou. Institute of Electrical and Electronics Engineers Inc., 2019. p. 74-79 8823362 (2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Leverage temporal convolutional network for the representation learning of URLs

AU - Liang, Yunji

AU - Kang, Jian

AU - Yu, Zhiwen

AU - Guo, Bin

AU - Zheng, Xiaolong

AU - He, Saike

PY - 2019/7

Y1 - 2019/7

N2 - 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%.

AB - 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%.

KW - Cyber Crime

KW - Temporal Convolutional Network

KW - URL Classification

KW - URL2vec

UR - https://www.scopus.com/pages/publications/85072973108

U2 - 10.1109/ISI.2019.8823362

DO - 10.1109/ISI.2019.8823362

M3 - 会议稿件

AN - SCOPUS:85072973108

T3 - 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019

SP - 74

EP - 79

BT - 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019

A2 - Zheng, Xiaolong

A2 - Abbasi, Ahmed

A2 - Chau, Michael

A2 - Wang, Alan

A2 - Zhou, Lina

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Conference on Intelligence and Security Informatics, ISI 2019

Y2 - 1 July 2019 through 3 July 2019

ER -

Liang Y, Kang J, Yu Z, Guo B, Zheng X, He S. Leverage temporal convolutional network for the representation learning of URLs. In Zheng X, Abbasi A, Chau M, Wang A, Zhou L, editors, 2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 74-79. 8823362. (2019 IEEE International Conference on Intelligence and Security Informatics, ISI 2019). doi: 10.1109/ISI.2019.8823362

Leverage temporal convolutional network for the representation learning of URLs

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this