CASIA OpenIR  > 智能感知与计算研究中心
DeepScan: Exploiting Deep Learning Malicious Account Detection in Location-Based Social Networks
Gong, Qingyuan1,2; Chen, Yang1,2; He, Xinlei1,2; Zhuang, Zhou1,2; Wang, Tianyi3; Huang, Hong4,5; Wang, Xin1,2; Fu, Xiaoming5
发表期刊IEEE COMMUNICATIONS MAGAZINE
ISSN0163-6804
2018-11-01
卷号56期号:11页码:21-27
通讯作者Gong, Qingyuan(qgong12@fudan.edu.cn)
摘要Our daily lives have been immersed in wide-spread location-based social networks (LBSNs). As an open platform LBSNs typically allow all kinds of users to register accounts. Malicious attackers can easily join and post misleading information often with the intention of influencing users' decisions in urban computing environments. To provide reliable information and improve the experience for legitimate users we design and implement DeepScan a malicious account detection system for LBSNs. Different from existing approaches DeepScan leverages emerging deep learning technologies to learn users' dynamic behavior. In particular we introduce the long short-term memory (LSTM) neural network to conduct time series analysis of user activities. DeepScan combines newly introduced time series features and a set of conventional features extracted from user activities and exploits a supervised machine-learning-based model for detection. Using real traces collected from Dianping a representative LBSN we demonstrate that DeepScan can achieve excellent prediction performance with an F1-score of 0.964. We also find that the time series features play a critical role in the detection system.
DOI10.1109/MCOM.2018.1700575
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61602122] ; National Natural Science Foundation of China[71731004] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61472423] ; Natural Science Foundation of Shanghai[16ZR1402200] ; Shanghai Pujiang Program[16PJ1400700] ; EU FP7 IRSES MobileCloud project[612212] ; Lindemann Foundation[12-2016]
项目资助者National Natural Science Foundation of China ; Natural Science Foundation of Shanghai ; Shanghai Pujiang Program ; EU FP7 IRSES MobileCloud project ; Lindemann Foundation
WOS研究方向Engineering ; Telecommunications
WOS类目Engineering, Electrical & Electronic ; Telecommunications
WOS记录号WOS:000450603000004
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22834
专题智能感知与计算研究中心
通讯作者Gong, Qingyuan
作者单位1.Fudan Univ, Sch Comp Sci, Shanghai Key Lab Intelligent Informat Proc, Shanghai, Peoples R China
2.Xidian Univ, State Key Lab Integrated Serv Networks, Xian, Shaanxi, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing Bytedance Technol & Res Ctr Precis Sening, Beijing, Peoples R China
4.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Hubei, Peoples R China
5.Univ Gottingen, Inst Comp Sci, Gottingen, Germany
推荐引用方式
GB/T 7714
Gong, Qingyuan,Chen, Yang,He, Xinlei,et al. DeepScan: Exploiting Deep Learning Malicious Account Detection in Location-Based Social Networks[J]. IEEE COMMUNICATIONS MAGAZINE,2018,56(11):21-27.
APA Gong, Qingyuan.,Chen, Yang.,He, Xinlei.,Zhuang, Zhou.,Wang, Tianyi.,...&Fu, Xiaoming.(2018).DeepScan: Exploiting Deep Learning Malicious Account Detection in Location-Based Social Networks.IEEE COMMUNICATIONS MAGAZINE,56(11),21-27.
MLA Gong, Qingyuan,et al."DeepScan: Exploiting Deep Learning Malicious Account Detection in Location-Based Social Networks".IEEE COMMUNICATIONS MAGAZINE 56.11(2018):21-27.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Gong, Qingyuan]的文章
[Chen, Yang]的文章
[He, Xinlei]的文章
百度学术
百度学术中相似的文章
[Gong, Qingyuan]的文章
[Chen, Yang]的文章
[He, Xinlei]的文章
必应学术
必应学术中相似的文章
[Gong, Qingyuan]的文章
[Chen, Yang]的文章
[He, Xinlei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。