讲座名称：Big Data Analysis and Security for Mobile Social Networks
讲座人：Dr. Kuan Zhang
Dr. Kuan Zhang received his Ph.D. degree in Electrical and ComputerEngineering from the University of Waterloo, Canada, in 2016. He received B.Sc.degree in Communication Engineering and M.Sc. degree in Computer Science fromNortheastern University, China, in 2009 and 2011, respectively. He is apostdoctoral fellow with the Department of Electrical and Computer Engineering,University of Waterloo, from August 2016 to July 2017. Dr. Zhang will be anAssistant Professor at the Department of Electrical and Computer Engineering,University of Nebraska, Lincoln. His research interests include big dataanalysis and security for mobile social networks, mobile healthcare, cyberphysical system, and cloud computing.
Dr. Kuan Zhang has authored/coauthored 26 journalpapers including IEEE Transaction on Wireless Communications, Dependable andSecure Computing, Industrial Informatics, Computational Social Systems, EmergingTopics in Computing, Selected Areas in Communications, IEEE Network Magazine,Information Sciences and 20 technical papers in conference proceedings includingIEEE INFOCOM, IEEE ICC and IEEE Globecom. He won the best paper awards of EAISecurecomm 2016 and IEEE WCNC 2017. He published 2 books. He served as a TPCmember for IEEE VTC, Globecom, ICC and the technical reviewer for multiple IEEETransactions including TPDS, TVT, TCC, and so on.
Mobile Social Network (MSN), as an emerging social network platform, has become increasingly popular and brought immense benefits. However, big data challenges and security concerns rise as the boom of MSN applications comes up. In this talk, we will present big data and security challenges in MSNs, and introduce big data analysis solutions. First, to detect misbehaviors during data sharing, we present a social-based mobile Sybil detection scheme (SMSD). The SMSD analyzes user’s social behaviors during networking and detects Sybil attackers by differentiating the abnormal pseudonym changing and contact behaviors, since Sybil attackers usually frequently or rapidly change their pseudonyms to cheat legitimate users. Then, we introduce a social network based infection analysis system, to analyze the instantaneous infectivity during human-to-human contact. We also present privacy-preserving data query and classification methods to achieve big data analysis and privacy in this infection analysis system. This talk will close with a brief discussion of future work on big data and security.