信息网络安全 ›› 2023, Vol. 23 ›› Issue (11): 1-8.doi: 10.3969/j.issn.1671-1122.2023.11.001

• 等级保护 • 上一篇    下一篇

基于多元时序特征的恶意域名检测方法

姚远1,2,3, 樊昭杉1,2, 王青1,2, 陶源4()   

  1. 1.中国科学院信息工程研究所,北京 100085
    2.中国科学院大学网络空间安全学院,北京 100049
    3.国家互联网应急中心湖北分中心,武汉 430072
    4.公安部第三研究所,上海 200031
  • 收稿日期:2023-05-06 出版日期:2023-11-10 发布日期:2023-11-10
  • 通讯作者: 陶源 taoyuan@gass.ac.cn
  • 作者简介:姚远(1976—),男,四川,高级工程师,博士,主要研究方向为目标识别和信息安全|樊昭杉(1997—),女,吉林,硕士,主要研究方向为恶意域名检测|王青(1995—),女,河南,博士,主要研究方向为网络空间安全、恶意域名检测|陶源(1981—),男,江苏,副研究员,博士,主要研究方向为网络安全等级保护、关键信息基础设施保护和人工智能安全
  • 基金资助:
    国家重点研发计划(2021YFF0307203);网络安全等级保护与安全保卫技术国家工程研究中心开放课题(C21640-3)

Malicious Domain Detection Method Based on Multivariate Time-Series Features

YAO Yuan1,2,3, FAN Zhaoshan1,2, WANG Qing1,2, TAO Yuan4()   

  1. 1. Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100085, China
    2. School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China
    3. Hubei Branch of The National Internet Emergency Center of China, Wuhan 430072, China
    4. The Third Research Institute of the Ministry of Public Security, Shanghai 200031, China
  • Received:2023-05-06 Online:2023-11-10 Published:2023-11-10

摘要:

当前,作为主要攻击媒介的恶意域名被广泛滥用于多种网络攻击活动中,针对恶意域名检测中检测特征设计复杂、需要经验知识辅助以及容易被攻击者有针对性绕过等问题,文章提出一种基于多元时序特征的恶意域名检测方法。该方法使用基于融合长短期记忆网络和全卷积神经网络的深度学习模型,分别从客户端请求和域名解析流量中自动化提取多元时序嵌入特征,并学习恶意域名行为的低维时序表示。对比传统的时间统计特征方案或时间序列局部模式判别方案,该方法可以建模长期域名活动模式,从中发现恶意域名区别于正常域名的行为序列,具有更强大的恶意域名检测能力。同时,该方法支持融合多元时序嵌入特征和通用恶意域名检测特征,多维度表征恶意行为信息,提升检测性能以及模型鲁棒性和扩展能力。

关键词: 恶意域名, 长短期记忆网络, 全卷积神经网络, 多元时序特征, 特征融合

Abstract:

At present, malicious domains as the main attack vector are widely abused in a variety of network attack activities. To address the problems of complex design of detection features in malicious domain detection, the need for empirical knowledge assistance and the ease of targeted bypassing by attackers, the paper proposed a malicious domain detection method based on multivariate temporal features. The method uses a deep learning model based on fused long and short-term memory networks and full convolutional neural networks to automatically extract multivariate temporal embedding features from client requests and domain resolution traffic, respectively, and learn low-dimensional temporal representations of malicious domain behaviors. Compared with traditional time-statistical feature schemes or time-series local pattern discrimination schemes, this method can establish long-term domain activity patterns and distinguish the behavior sequences of malicious domains from normal domains, which has more powerful malicious domain detection capability. Meanwhile, the method supports the fusion of multivariate time-series embedding features and generic malicious domain detection features to characterize malicious behavior information in multiple dimensions, improving detection performance as well as model robustness and scalability.

Key words: malicious domain, long short-term memory, fully convolutional network, multivariate time-series feature, feature fusion

中图分类号: