I am currently a Computer Science Ph.D. student in Big Data and Social Computing (BDSC) Lab of the University of Illinois at Chicago. My supervisor is Prof. Philip S. Yu. Before joining UIC, I received my B.E. from BUPT and QMUL. My research interests are graph mining, spam detection and social network analysis.
- A Novel Centrality Cascading Based Edge Parameter Evaluation Method for Robust Influence Maximization.
Xiaolong Deng, Yingtong Dou, Tiejun Lv, Nguyen QVH.
IEEE Access. 2017.
- CPS Model Based Online Opinion Governance Modeling and Evaluation of Emergency Accidents.
Xiaolong Deng, Yingtong Dou, Yihua Huang.
EMGIS in ACM SIGSPATIAL. 2016.
[Paper][Slides][Extended Journal Version][BibTeX]
- Suspicious Behavior Modeling in Mobile App Markets
Introduction Mobile App Markets like App Store and Google Play involves many fraudsters like spammers, botnets and crowd workers. We investigate the underground market of trading app downloads and reviews, and aim to design classifers with multi-view and multi-source information according to the intention of the fraudsters.
Resources My intro slides about graph-based spam detection, Meng Jiang’s survey on suspicious behavior modeling, Srijan Kumar’s survey on online false information study.
- Securing Graph-based Classfication Model
Introduction It is a long lasting campaign between the fraudsters and online review platforms like Yelp and TripAdvisor. We aim to improve the robustness of graphical classfiers and representation learning frameworks against various kinds of adversarial tactics.
Resources A survey from our lab on adversarial attack and defense on graph data, KDD18 best paper on adversarial attack on neural networks for graph data, ICML18 paper on adversarial attack on graph structured data.
- [1/2019] Move my personal website from Wordpress to Github.
- [1/2019] Give a talk about graph based spammer detection at Tencent.
- [5/2018] Start summer intern at the Search and Recommendation Group of Noah’s Ark Lab.
- [2/2018] Publish a dataset with Chinese O2O service Wechat lucky package sharing log between two years.