Defending against user identity linkage: Build an effective User Accounts Linkage Inference (UALI) model to link accounts in multiple online social networks (OSNs) to exemplify potential risks of account linkage. Develop Resist User LinkagE (RULE) algorithm to study the countermeasure against user identity linkage attack across multiple OSNs. (Patent Submitted).
Selected Publications
Collective Geographical Embedding for Geolocating Social Network Users
The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD),2017
DistSD: Distance-based Social Discovery with Personalized Posterior Screening
IEEE International Conference on Big Data (BigData),2016
Collaborative Co-clustering across Multiple Social Media
IEEE International Conference on Mobile Data Management (MDM),2016
Concurrent Goal-oriented Co-clustering Generation in Social Networks
IEEE International Conference on Semantic Computing (ICSC),2015
Why Checkins: Exploring User Motivation on Location Based Social Networks
IEEE International Conference on Data Mining (ICDM),2014.
Steering Information Diffusion Dynamically against User Attention Limitation
IEEE International Conference on Data Mining (ICDM),2014.
When and Where: Predicting Human Movements Based on Social Spatial-Temporal Events
SIAM International Conference on Data Mining (SDM),2014
Defending against User Identity Linkage Attack across Multiple Online Social Networks
International conference on World wide web companion (WWW Companion), 2014.
Extracting social events for learning better information diffusion models
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD),2013
Social Action Tracking via Noise Tolerant Time-varying Factor Graphs
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD),2010