
软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software, 2022,33(2):683 [doi: 10.13328/j.cnki.jos.006314] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563
一种基于图模型的网络攻击溯源方法
黄克振
1,2
,
连一峰
1
,
冯登国
1
,
张海霞
1
,
吴
迪
3
,
马向亮
4
1
(中国科学院 软件研究所 可信计算与信息保障实验室, 北京 100190)
2
(中国科学院大学, 北京 100049)
3
(中国网络安全审查技术与认证中心, 北京 100020)
4
(清华大学 集成电路学院, 北京 100084)
通信作者: 黄克振, E-mail: kezhen@iscas.ac.cn
摘 要: 随着信息技术的飞速发展, 网络攻击事件频发, 造成了日益严重的经济损失或社会影响. 为了减少损失
或预防未来潜在的攻击, 需要对网络攻击事件进行溯源以实现对攻击者的挖掘追责. 当前的溯源过程主要依赖于
人工完成, 效率低下. 面对日益增加的海量溯源数据和日趋全面的溯源建模分析维度, 亟需半自动化或自动化的
网络攻击者挖掘方法. 提出一种基于图模型的网络攻击溯源方法, 建立网络攻击事件溯源本体模型, 融合网络攻
击事件中提取的线索数据和威胁情报数据, 形成网络攻击事件溯源关系图; 引入图嵌入算法自动学习嵌有关联线
索特征的网络攻击事件特征向量, 进而利用历史网络攻击事件特征向量训练 SVM(support vector machine)分类器,
并基于 SVM 分类器完成网络攻击者的挖掘溯源; 最后, 通过实验验证了该方法的可行性和有效性.
关键词: 网络攻击事件; 网络攻击者; 溯源; 网络攻击事件溯源; 关系图; 图嵌入
中图法分类号: TP309
中文引用格式: 黄克振, 连一峰, 冯登国, 张海霞, 吴迪, 马向亮. 一种基于图模型的网络攻击溯源方法. 软件学报, 2022,
33(2): 683–698. http ://www.jos.org.cn/1000-9825/6314.h tm
英文引用格式: Huang KZ, Lian YF, Feng DG, Zhang HX, Wu D, Ma XL. Method of Cyber Attack Attribution Based on Graph
Model. Ruan Jian Xue Bao/Journal of Software, 2022, 33(2): 683698 (in Chinese). http://www.jos.org.cn/1000-9825/6314.htm
Method of Cyber Attack Attributio n Based on Gr aph Model
HUANG Ke-Zhen
1,2
, LIAN Yi-Feng
1
, FENG Deng-Guo
1
, ZHANG Hai-Xia
1
, WU Di
3
, MA Xiang-Liang
4
1
(Trusted Computing and Information Assur ance Laboratory, Insti tute of So ftware, Chinese Academy o f Sci ences, Beijing 100190 , China)
2
(University of Chinese Academy of S ciences, Beijing 10 0049, Chin a)
3
(China Cybersecurity Review Technology and Certification Center, Beijing 100020, China)
4
(School of Integrated Circuits , Tsing hua University, Beijing 100084, China)
Abstra ct : With the rapid development of technologies such as computers and smart devices, cyber attack incidents happen frequently,
which cause increasingly serious economic losses or reputation losses. In order to reduce losses and prevent future potenti al attacks, it is
necessary to trace the source of cyber attack incidents to achieve accountability for the attackers. The attribution of cyber attackers is
mainly a manual process by forensic analyst. Faced with increasing analysis data and analysis dimensions, semi-automated or automated
cyber attackers mining analysis methods are urgently needed. This study proposes a graph model-based attacker mining analysis method
for cyber attack incidents. This method first establishes an ontology model for cyber attack incident attribution, and then fuses clue data
extracted from cyber attack incidents with various threat intelligence data to construct a cyber attack incidents attribution relationship
graph. The graph embedding algorithm automatically learns the representation vector of cyber attack incidents, which embedded clue
characteristics of cyber attack incidents, from the attribution relationship graph of cyber attack incidents. And then a classifier is trained
with th e hist ori cal cyber atta ck in cide nts r epres ent ation vect or, which c lass ifi es th e cyber att ack in cid ent to one c yber atta cker. Finally, the
基金项目: 国家重点研发计划(2020YFB1806504, 2018YFC0824801)
收稿时间: 2020-06-23; 修改时间: 2020-09-27, 2020-11-24; 采用时间: 2021-01-10; jos 在线出版时间: 2021-08-03
评论