Hailu Xu

School of Computing and Information Sciences

Lecture Information:
  • November 19, 2019
  • 11:00 AM
  • CASE 349

Speaker Bio

Hailu Xu is a Ph.D. candidate in the School of Computing and Information Sciences (SCIS) at Florida International University (FIU). He is working under the direction of Dr. Liting Hu in the Elves Lab. His research interests are in the Operating System, Cloud Computing, and Big Data System.


Malicious URL links, fraudulent advertisements, faked reviews, and biased propaganda are bringing serious consequences for both virtual social networks and human life in the real world. Effectively detecting social spam is a hot topic in both academia and industry. However, traditional social spam detection techniques are limited to centralized processing on top of one specific data source, but ignore the social spam correlations of distributed data sources. We propose an online and scalable spam detection system, named Spiral, to uncover social spam by leveraging the correlations between different social data sources in geo-distributed sites. The novelty of our design lies in three key components: (1) adecentralized distributed hash table (DHT) based tree overlay deployment for harvesting and uncovering deceptive spam in many online social networks communities; (2) a progressive aggregation tree for aggregating the properties of these spam posts and creating new spam classifiers to actively filter out newest spam; and (3) a group communication structure that allows multiple groups to exchange and utilize the correlations among distributed social data sources. Our large-scale experiments using real-world social data demonstrate Spiral’s scalability, attractive load-balancing, and graceful efficiency in online spam detection for social networks.