Towards Online Spam Filtering in Social Networks

Wednesdays@NICO Seminar, Noon, March 28 2012, Chambers Hall, Lower Level

Prof. Yan Chen, Northwestern University


Online social networks (OSNs) are extremely popular among Internet users. Unfortunately, in the wrong hands, they are also effective tools for executing spam campaigns. In this paper, we present an online spam filtering system that can be deployed as a component of the OSN platform to inspect messages generated by users in real-time. We propose to reconstruct spam messages into campaigns for classification rather than examine them individually. We evaluate the system using 187 million wall posts collected from Facebook and 17 million tweets collected from Twitter. The true positive rate reaches 80.9% while the false positive rate reaches 0.19%. In addition, it stays accurate for more than 9 months after the initial training phase. Finally, tested on a normal server, the system achieves an average throughput of 1580 messages/sec and an average processing latency of 21.5ms on the Facebook dataset.


Dr. Yan Chen is an Associate Professor in the Department of Electrical Engineering and Computer Science at Northwestern University, Evanston, IL. He received his Ph.D. in Computer Science at University of California at Berkeley in 2003. His research interests include network security (including Web 2.0, Online Social Networks, and smartphone security) and data center networks. He won the Depart-ment of Energy (DoE) Early CAREER award in 2005, the Department of Defense (DoD) Young Investigator Award in 2007, and the Microsoft Trustworthy Computing Awards in 2004 and 2005 with his colleagues. Based on Google Scholar, his papers have been cited over 4,000 times. More Information can be found at