Open Access

ARTICLE

A Convolution-Based System for Malicious URLs Detection

Chaochao Luo¹, Shen Su^{2, *}, Yanbin Sun², Qingji Tan³, Meng Han⁴, Zhihong Tian^{2, *}
1 Institute of Computer Application, China Academy of Engineering Physics, Mianyang, 621054, China.
2 Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006, China.
3 School of Mechanical and Electrical Engineering, Heilongjiang State Farm Science Technology Vocational College, Harbin, 150431, China.
4 Department of Computing and Software Engineering, Kennesaw State University, Kennesaw, GA 30144, USA.
* Corresponding Authors: Shen Su. Email: ;
  Zhihong Tian. Email: .

Computers, Materials & Continua 2020, 62(1), 399-411. https://doi.org/10.32604/cmc.2020.06507

Abstract

Since the web service is essential in daily lives, cyber security becomes more and more important in this digital world. Malicious Uniform Resource Locator (URL) is a common and serious threat to cybersecurity. It hosts unsolicited content and lure unsuspecting users to become victim of scams, such as theft of private information, monetary loss, and malware installation. Thus, it is imperative to detect such threats. However, traditional approaches for malicious URLs detection that based on the blacklists are easy to be bypassed and lack the ability to detect newly generated malicious URLs. In this paper, we propose a novel malicious URL detection method based on deep learning model to protect against web attacks. Specifically, we firstly use auto-encoder to represent URLs. Then, the represented URLs will be input into a proposed composite neural network for detection. In order to evaluate the proposed system, we made extensive experiments on HTTP CSIC2010 dataset and a dataset we collected, and the experimental results show the effectiveness of the proposed approach.

---

Keywords

CNN, anomaly detection, web security, auto-encoder, deep learning.

---

Citations