Robust Detection of Malicious URLs With Self-Paced Wide & Deep Learning

doi:10.1109/TDSC.2021.3121388

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 互联网大数据与信息安全

	Robust Detection of Malicious URLs With Self-Paced Wide & Deep Learning
	Liang, Yunji 1; Wang, Qiushi 1; Xiong, Kang 1; Zheng, Xiaolong2 ; Yu, Zhiwen 1; Zeng, Daniel2
发表期刊	IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
ISSN	1545-5971
	2022-03-01
卷号	19 期号:2 页码:717-730
通讯作者	Liang, Yunji(liangyunji@nwpu.edu.cn)
摘要	As cybercrimes grow in scale with devastating economic costs, it is important to protect potential victims against diverse attacks. In spite of the diversity of cybercrimes, it is the uniform resource locators (URLs) that connect vulnerable users with potential attacks. Although numerous solutions (e.g., rule-based solutions and machine learning-based methods) are proposed for malicious URL detection, they cannot provide robust performance due to the diversity of cybercrimes and cannot cope with the explosive growth of malicious URLs with the evolution of obfuscation strategies. In this paper, we propose a deep learning-based system, dubbed as CyberLen, to detect malicious URLs robustly and effectively. Specifically, we use factorization machine (FM) to learn the latent interaction among lexical features. For the deep structural features, position embedding is introduced for token vectorization to reduce the ambiguity of URL tokens. Meanwhile, temporal convolution network (TCN) is utilized to learn the long-distance dependency among URL tokens. To fuse heterogeneous features, self-paced wide & deep learning strategy is proposed to train a robust model effectively. The proposed solution is evaluated on a large-scale URL dataset. Our experimental results show that position embedding is constructive to reducing the ambiguity of URL tokens, and the self-paced wide & deep learning strategy shows superior performance in terms of F1 score and convergence speed.
关键词	paced learning temporal convolutional network factorization machine wide & deep malicious URL detection
DOI	10.1109/TDSC.2021.3121388
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2018AAA0100500] ; Natural Science Foundation of China[61902320] ; Fundamental Research Funds for the Central Universities[31020180QD140]
项目资助者	National Key Research and Development Program ; Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000767856000001
出版者	IEEE COMPUTER SOC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48079
专题	多模态人工智能系统全国重点实验室_互联网大数据与信息安全
通讯作者	Liang, Yunji
作者单位	1.Northwestern Polytech Univ, Sch Comp Sci, Xian 710060, Shaanxi, Peoples R China 2.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Liang, Yunji,Wang, Qiushi,Xiong, Kang,et al. Robust Detection of Malicious URLs With Self-Paced Wide & Deep Learning[J]. IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING,2022,19(2):717-730.
APA	Liang, Yunji,Wang, Qiushi,Xiong, Kang,Zheng, Xiaolong,Yu, Zhiwen,&Zeng, Daniel.(2022).Robust Detection of Malicious URLs With Self-Paced Wide & Deep Learning.IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING,19(2),717-730.
MLA	Liang, Yunji,et al."Robust Detection of Malicious URLs With Self-Paced Wide & Deep Learning".IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 19.2(2022):717-730.