加入收藏夹
联系我们
关于本站
个人主页
西电导航
西安电子科技大学
    当前位置:首页>>学术讲座
DeepScan: Exploiting Deep Learning for Malicious Account Detection in Location-Based Social Networks
时间:2017-12-26 09:45    点击:   所属单位:通信工程学院
讲座名称 DeepScan: Exploiting Deep Learning for Malicious Account Detection in Location-Based Social Networks
讲座时间 2017-12-28 10:30:00
讲座地点 北校区科技楼B301会议室
讲座人 陈阳
讲座人介绍 Yang Chen is a Pre-tenure Associate Professor within the School of Computer Science at Fudan University. From April 2011 to September 2014, he was a postdoctoral associate at the Department of Computer Science, Duke University, USA, where he served as Senior Personnel in the NSF MobilityFirst project. From September 2009 to April 2011, he has been a research associate and the deputy head of Computer Networks Group, Institute of Computer Science, University of Goettingen, Germany. He received his B.S. and Ph.D. degrees from Department of Electronic Engineering, Tsinghua University in 2004 and 2009, respectively. He visited Stanford University (in 2007) and Microsoft Research Asia (2006-2008) as a visiting student. His research interests include online social networks, Internet architecture and mobile computing. He is serving as an Associate Editor of IEEE Access and an Editorial Board Member of the Transactions on Emerging Telecommunications Technologies (ETT). He served as a OC / TPC Member for many international conferences, including SOSP, WWW, IJCAI, AAAI, IWQoS, ICCCN, GLOBECOM and ICC. He published more than 50 referred papers in international journals and conferences, including IEEE TPDS, IEEE TSC, IEEE TNSM, IEEE Communications Magazine, Middleware, INFOCOM, ICDE, COSN, CIKM and IWQoS. He is a senior member of the IEEE.
讲座内容

The widespread location-based social networks (LBSNs) have immersed into our daily life. 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 the users' decision 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 the real traces collected from Dianping, a representative LBSN, we demonstrate that DeepScan can achieve an excellent prediction performance with an F1-score of 0.981. We also find that the time series features play a critical role in the detection system.

转载请注明出处:西安电子科技大学学术信息网
如果您有学术信息或学术动态,欢迎投稿。我们将在第一时间确认并收录,投稿邮箱: meeting@xidian.edu.cn
Copyright © 2011-2017 西安电子科技大学 
开发维护:电子工程学院网络信息中心  管理员:meeting@xidian.edu.cn 站长统计: