社交网络关键黑客节点识别方法

doi:10.3969/j.issn.1671-1122.2023.01.007

信息网络安全 ›› 2023, Vol. 23 ›› Issue (1): 57-65.doi: 10.3969/j.issn.1671-1122.2023.01.007

社交网络关键黑客节点识别方法

马相军¹, 何泾沙¹(), 吴铁军², 范敦球²

1.北京工业大学信息学部，北京 100124
2.绿盟科技集团股份有限公司，北京 100089

收稿日期:2022-10-18 出版日期:2023-01-10 发布日期:2023-01-19
通讯作者: 何泾沙 E-mail:jhe@bjut.edu.cn
作者简介:马相军（1982—），男，山东，博士研究生，主要研究方向为网络安全、社交网络分析|何泾沙（1961—），男，陕西，教授，博士，主要研究方向为计算机和网络安全、测试与分析和云计算|吴铁军（1978—），男，湖北，研究员，硕士，主要研究方向为入侵检测、威胁线索推理|范敦球（1978—），男，福建，研究员，硕士，主要研究方向为威胁情报分析、APT追踪溯源
基金资助:
国家自然科学基金(61602456);CCF-绿盟科技“鲲鹏”科研基金(CCF-NSFOCUS 2021004)

An Approach to Identifying Key Hackers in Social Networks

MA Xiangjun¹, HE Jingsha¹(), WU Tiejun², FAN Dunqiu²

1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
2. NSFOCUS Technologies Group Co., Ltd., Beijing 100089, China

Received:2022-10-18 Online:2023-01-10 Published:2023-01-19
Contact: HE Jingsha E-mail:jhe@bjut.edu.cn

摘要/Abstract

摘要：

计算机网络安全形势严峻，对实施网络攻击的黑客以及黑客所在组织的研究越来越重要。社交网络有不受时间空间限制的特点，因此成为黑客交流的主要平台，也是网络安全研究人员获取信息的重要渠道。为了对社交网络中的黑客进行分析，文章提出一种基于社区发现的社交网络关键黑客节点识别方法。首先，文章通过图卷积网络以无监督方式实现网络的社区划分；然后，利用用户之间的交互行为和主题相似度，通过改进的PageRank算法实现社区内黑客节点的影响力度量；最后，通过独立级联模型评估关键黑客节点对网络传播效率的作用。在Twitter数据集上的实验表明，该方法能有效识别社交网络中的关键黑客用户。

关键词: 关键黑客节点识别, 影响力度量, 社区发现, 社交网络分析

Abstract:

The situation of computer network security is very serious, so the research on the hackers who carry out network attacks and the organizations where the hackers are located becomes more and more important. Social networks have become the main platform for hackers to communicate with each other and an important channel for network security researchers to obtain information because of their characteristics of not being restricted by time and space. In order to analyze the hackers in social networks, this paper proposed a community detection-based method for identifying key hackers in social networks. Firstly, the article imlemented community segmentation of the network in an unsupervised manner through graph convolutional networks. Secondly, through the improved PageRank algorithm, the topic similarity and interaction between users were used to measure the influence of users in the community. Finally, the efficiency of key hackers in network propagation was evaluated through an independent cascade model. Experiments on the Twitter dataset show that the method can effectively identify key hacker users in social networks.

Key words: key hacker node identification, impact metrics, community detection, social network analysis

中图分类号:

TP309

马相军, 何泾沙, 吴铁军, 范敦球. 社交网络关键黑客节点识别方法[J]. 信息网络安全, 2023, 23(1): 57-65.

MA Xiangjun, HE Jingsha, WU Tiejun, FAN Dunqiu. An Approach to Identifying Key Hackers in Social Networks[J]. Netinfo Security, 2023, 23(1): 57-65.

图/表 5

参考文献 16

[1]	LI Ying, CHENG Jiaxing, HUANG Cheng, et al. NEDetector: Automatically Extracting Cybersecurity Neologisms from Hacker Forums[J]. Journal of Information Security and Applications, 2021, 58(5): 102784-102797. doi: 10.1016/j.jisa.2021.102784 URL
[2]	NATARAJAN N, SEN P, CHAOJI V. Community Detection in Content-Sharing Social Networks[C]// IEEE. 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. New York: IEEE, 2013: 82-89.
[3]	SHI Huaijing. Research on Online Public Opinion Management Mechanism of Public Security Emergencies in Micro-Communication Environment[D]. Chongqing: Sichuan International Studies University, 2019.
	石怀静. 微传播环境下突发公共安全事件网络舆情管理机制研究[D]. 重庆: 四川外国语大学, 2019.
[4]	TEO L X, LENG H K, PHUA Y X P. Marketing on Instagram: Social Influence and Image Quality on Perception of Quality and Purchase Intention[J]. International Journal of Sports Marketing and Sponsorship, 2019, 20(2): 321-332. doi: 10.1108/IJSMS-04-2018-0028 URL
[5]	BERAHMAND K, NASIRI E, FOROUZANDEH S, et al. A Preference Random Walk Algorithm for Link Prediction Through Mutual Influence Nodes in Complex Networks[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(8): 5375-5387. doi: 10.1016/j.jksuci.2021.05.006 URL
[6]	VERBERT K, MANOUSELIS N, OCHOA X, et al. Context-Aware Recommender Systems for Learning: a Survey and Future Challenges[J]. IEEE Transactions on Learning Technologies, 2012, 5(4): 318-335. doi: 10.1109/TLT.2012.11 URL
[7]	HOLT T J. Examining the Forces Shaping Cybercrime Markets Online[J]. Social Science Computer Review, 2013, 31(2): 165-177. doi: 10.1177/0894439312452998 URL
[8]	PETE I, HUGHES J, CHUA Y T, et al. A Social Network Analysis and Comparison of Six Dark Web Forums[C]// IEEE. IEEE European Symposium on Security and Privacy. New York: IEEE, 2020: 484-493.
[9]	HUANG Cheng, GUO Yongyan, GUO Wenbo, et al. HackerRank: Identifying Key Hackers in Underground Forums[EB/OL]. (2021-05-04)[2022-10-17]. https://doi.org/10.1177/15501477211015145.htm.
[10]	GRISHAM J, SAMTANI S, PATTON M, et al. Identifying Mobile Malware and Key Threat Actors in Online Hacker Forums for Proactive Cyber Threat Intelligence[C]// IEEE. 15th IEEE International Conference on Intelligence and Security Informatics-Security and Big Data (ISI). New York: IEEE, 2017: 13-18.
[11]	MARIN E, SHAKARIAN J, SHAKARIAN P. Mining Key-Hackers on Darkweb Forums[C]// IEEE. 1st International Conference on Data Intelligence and Security (ICDIS). New York: IEEE, 2018: 73-80.
[12]	ZHANG Yiming, FAN Yujie, YE Yanfang, et al. KADetector: Automatic Identification of Key Actors in Online Hack Forums Based on Structured Heterogeneous Information Network[C]// IEEE. 9th IEEE International Conference on Big Knowledge (ICBK). New York: IEEE, 2018: 154-161.
[13]	HE Dongxiao, SONG Yue, JIN Di, et al. Community-Centric Graph Convolutional Network for Unsupervised Community Detection[C]// IJCAI. 29th International Joint Conference on Artificial Intelligence. San Francisco: IJCAI, 2021: 3515-3521.
[14]	JIN Di, LIU Ziyang, LI Weihao, et al. Graph Convolutional Networks Meet Markov Random Fields: Semi-Supervised Community Detection in Attribute Networks[C]// Assoc Advancement Artificial Intelligence. 33rd AAAI Conference on Artificial Intelligence. New York: AAAI, 2019: 152-159.
[15]	BABKO-MALAYA O, CATHEY R, HINTON S, et al. Detection of Hacking Behaviors and Communication Patterns on Social Media[C]// IEEE. IEEE International Conference on Big Data (IEEE Big Data). New York: IEEE, 2017: 4636-4641.
[16]	FANG Zhen, ZHAO Xinyi, WEI Qiang, et al. Exploring Key Hackers and Cybersecurity Threats in Chinese Hacker Communities[C]// IEEE. 14th IEEE International Conference on Intelligence and Security Informatics-Cybersecurity and Big Data (IEEE ISI). New York: IEEE, 2016: 13-18.

数据项	数量	说明
用户数	124907	已清理机构账号和被判定为滥用关注关系的账号
推文数	2013215	用户近3个月发布的推文
好友关系总数	22674920	包括关注和被关注2种关系

社交网络关键黑客节点识别方法

An Approach to Identifying Key Hackers in Social Networks

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 16

相关文章 5

编辑推荐

Metrics

本文评价

[1]	慕志颖, 许加全, 李晓宇. 基于社区发现的社交网络影响力阻断最大化算法[J]. 信息网络安全, 2023, 23(1): 44-56.
[2]	周玉晶, 沈嘉荟, 邱海韬, 查达仁. 基于复杂网络的社交媒体内容安全可视化分析系统[J]. 信息网络安全, 2016, 16(9): 158-162.
[3]	温俊伟. 面向Twitter的分析系统研究[J]. 信息网络安全, 2016, 16(9): 234-239.
[4]	许为, 林柏钢, 林思娟, 杨旸. 一种基于用户交互行为和相似度的社交网络社区发现方法研究[J]. 信息网络安全, 2015, 15(7): 77-83.
[5]	. 社交网Twitter平台的人物关系网社区发现[J]. , 2014, 14(5): 32-.