面向网络公害社群的社交网络特性分析方法

王博; 郭捷; 邱卫东; 黄征

doi:10.11959/j.issn.2096-109x.2024041

您当前的位置：

首页 >

文章列表页 >

面向网络公害社群的社交网络特性分析方法

学术论文 | 更新时间：2024-08-14

- 面向网络公害社群的社交网络特性分析方法
- Analysis method on the properties of social networks of internet nuisance communities
- 网络与信息安全学报 2024年10卷第3期页码：81-90
- 作者机构：
  
  上海交通大学网络空间安全学院，上海 200240
- 作者简介：
  
  [ "王博（1997- ），男，山东潍坊人，上海交通大学硕士生，主要研究方向为人工智能安全、信息内容安全。" ]
  [ "郭捷（1976- ），女，河南南阳人，上海交通大学副研究员，主要研究方向为多媒体安全、人工智能安全、大数据隐私保护。" ]
  [ "邱卫东（1973- ），男，江西修水人，上海交通大学教授、博士生导师，主要研究方向为计算机取证、密码分析、人工智能安全、大数据隐私保护。" ]
  [ "黄征（1975- ），男，四川南充人，上海交通大学副教授，主要研究方向为人工智能、隐私保护计算。" ]
- 基金信息：
  
  国家自然科学基金;The National Natural Science Foundation of China(61972249)
- DOI：10.11959/j.issn.2096-109x.2024041
  中图分类号： TP393
- 收稿：2023-02-28，
  
  修回：2023-09-01，
  
  纸质出版：2024-06-25
- 稿件说明：
移动端阅览
王博, 郭捷, 邱卫东, 等. 面向网络公害社群的社交网络特性分析方法[J]. 网络与信息安全学报, 2024, 10(3): 81-90.

WANG B, GUO J, QIU W D, et al. Analysis method on the properties of social networks of internet nuisance communities[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 81-90.
王博, 郭捷, 邱卫东, 等. 面向网络公害社群的社交网络特性分析方法[J]. 网络与信息安全学报, 2024, 10(3): 81-90. DOI： 10.11959/j.issn.2096-109x.2024041.

WANG B, GUO J, QIU W D, et al. Analysis method on the properties of social networks of internet nuisance communities[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 81-90. DOI： 10.11959/j.issn.2096-109x.2024041.

摘要

随着网络的普及和网民群体的壮大，网络水军、网络公害社群等互联网公害组织严重威胁我国网络环境的安全。针对这类组织远离国内监管、隐蔽性和伪装性强的特点，提出了面向网络公害社群的社交网络特性分析方法。在用户特性层面，通过中心性测量对组内成员的影响力分布进行计算，找出影响力最大的核心用户，并分析核心成员的匿名性特点。在复杂网络特性层面，通过小世界效应和无标度特性的分析，研究了该社群内部的集群状况和资源分布状况。在时序特性层面，对核心成员的发文内容进行预处理后，利用BERTopic进行动态主题建模，得到社群主题随时间的变化关系。大量的实验性能分析验证了本文方法的有效性，研究成果可用于分析公害社群相关特征，追踪犯罪活动轨迹，为公害组织的侦查和打击工作以及自动化检测系统的设计工作提供理论参考。

Abstract

With the widespread adoption of the Internet and an increase in the number of Internet users

the security of the network environment has been seriously threatened by Internet public hazards organizations

such as the Internet water army and the internet public hazards community. Given the characteristics of these organizations

which include being distant from domestic supervision and possessing strong concealment and camouflage abilities

a social network characteristic analysis method was proposed for Internet public hazards organizations. Initially

at the user characteristic level

the influence distribution of group members was calculated through centrality measurement to identify the core users with the greatest influence

and an analysis of the anonymity characteristics of these core members was conducted. Subsequently

at the complex network characteristic level

the cluster status and resource distribution within the community were studied through the analysis of small-world effects and scale-free characteristics. Finally

at the temporal characteristic level

after preprocessing the post content of core members

BERTopic was utilized for dynamic topic modeling to ascertain the relationship between community themes and time. A large number of experimental performance analyses have verified the effectiveness of the proposed method. The research results can be utilized to analyze the characteristics of public hazard communities

track criminal activity trajectories

and provide theoretical references for the investigation and crackdown of public hazard organizations

as well as for the design of automated detection systems.

关键词

Keywords

references

中国互联网信息中心 . 第50次中国互联网发展状况统计报告 [R ] . 2022 .

CNNIC . The 50th statistical report on china's internet development [R ] . 2022 .

XU S , LIU X , MA K , et al . Rumor detection on social media using hierarchically aggregated feature via graph neural networks [J ] . Applied Intelligence , 2023 , 53 ( 3 ): 3136 - 3149 .

HE Y , YANG P , CHENG P . Semi-supervised internet water army detection based on graph embedding [J ] . Multimedia Tools and Applications , 2023 , 82 ( 7 ): 9891 - 9912 .

JIANG Y , LIU G , WU J , et al . Telecom fraud detection via hawkes-enhanced sequence model [J ] . IEEE Transactions on Knowledge and Data Engineering , 2022 , 35 ( 5 ): 5311 - 5324 .

DAI J , ZHU J , WANG G . Opinion influence maximization problem in online social networks based on group polarization effect [J ] . Information Sciences , 2022 , ( 609 ): 195 - 214 .

JONES K , NURSE J R C , LI S . Out of the shadows: analyzing anonymous' twitter resurgence during the 2020 black lives matter protests [C ] // Proceedings of the International AAAI Conference on Web and Social Media . 2022 , ( 16 ): 417 - 428 .

BADA M , NURSE J R C . Profiling the cybercriminal: a systematic review of research [C ] // 2021 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA) . 2021 : 1 - 8 .

JONES K , NURSE J R C , LI S . Behind the mask: a computational study of Anonymous' presence on Twitter [C ] // Proceedings of the International AAAI Conference on Web and Social Media . 2020 : 327 - 338 .

石俊峥 . 基于节点时空属性的移动应用网络行为分析技术研究 [D ] . 北京 : 中国科学院大学 , 2021 .

SHI J Z . Research on mobile application network behavior analysis technology based on node space-time attribute [D ] . Beijing : University of Chinese Academy of Sciences , 2021 .

CAMPANA P , VARESE F . Studying organized crime networks: data sources, boundaries and the limits of structural measures [J ] . Social networks , 2022 , 69 : 149 - 159 .

吕芳 , 张新琳 , 王巍 , 等 . 银行账户交易复杂网络特性分析 [J ] . 网络与信息安全学报 , 2019 , 5 ( 4 ): 99 - 107 .

LYU F , ZHANG X L , WANG W , et al . Analyzing the complex properties of bank account transaction network [J ] . Chinese Journal of Network and Information Security , 2019 , 5 ( 4 ): 99 - 107 .

KIGERL A . Behind the scenes of the underworld: hierarchical clustering of two leaked carding forum databases [J ] . Social Science Computer Review , 2022 , 40 ( 3 ): 618 - 640 .

GROOTENDORST M . BERTopic: neural topic modeling with a class-based TF-IDF procedure [J ] . arXiv Preprint arXiv: 2203. 05794 , 2022 .

MILGRAM S . The small world problem [J ] . Psychology Today , 1967 , 2 ( 1 ): 60 - 67 .

NEWMAN M E J , MOORE C , WATTS D J . Mean-field solution of the small-world network model [J ] . Physical Review Letters , 2000 , 84 ( 14 ): 3201 .

SPORNS O , ZWI J D . The small world of the cerebral cortex [J ] . Neuroinformatics , 2004 , 2 : 145 - 162 .

BARABÁSI A L , ALBERT R . Emergence of scaling in random networks [J ] . Science , 1999 , 286 ( 5439 ): 509 - 512 .

SHARMA S , BATRA N . Comparative study of single linkage, complete linkage, and ward method of agglomerative clustering [C ] // 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon) . 2019 : 568 - 573 .

REIMERS N , GUREVYCH I . Sentence-BERT: sentence embeddings using siamese BERT-networks [C ] // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . 2019 : 3982 - 3992 .

MCINNES L , HEALY J , SAUL N , et al . UMAP: uniform manifold approximation and projection [J ] . Journal of Open Source Software , 2018 , 3 ( 29 ): 861 .

KIM D , SEO D , CHO S , et al . Multi-co-training for document classification using various document representations: TF-IDF, LDA, and Doc2Vec [J ] . Information Sciences , 2019 , 477 : 15 - 29 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据