Cost-Sensitive Learning by Cost-Proportionate Example Weighting
ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Modeling and Simulation Study of the Propagation and Defense of Internet E-mail Worms
IEEE Transactions on Dependable and Secure Computing
Spamming botnets: signatures and characteristics
Proceedings of the ACM SIGCOMM 2008 conference on Data communication
@spam: the underground on 140 characters or less
Proceedings of the 17th ACM conference on Computer and communications security
Detecting and characterizing social spam campaigns
IMC '10 Proceedings of the 10th ACM SIGCOMM conference on Internet measurement
Detecting spammers on social networks
Proceedings of the 26th Annual Computer Security Applications Conference
| Hi-index | 0.00 |
Online social networks (OSNs) are popular collaboration and communication tools for millions of users and their friends. 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. Although campaign identification has been used for offline spam analysis, we apply this technique to aid the online spam detection problem with sufficiently low overhead. Accordingly, our system adopts a set of novel features that effectively distinguish spam campaigns. It is highly accurate and confidently drops messages classified as "spam" before they reach the intended recipients, thus protecting them from various kinds of fraud. In addition, the system achieves an average throughput of 1580 messages/sec and an average processing latency of 69.7ms for each message. The high throughput and low latency guarantees that it will not become the bottleneck of the whole OSN platform.