head

Publications (Back to Homepage)

2021

2020

Before 2020

  • Uncovering Download Fraud Activities in Mobile App Markets.
    Yingtong Dou, Weijian Li, Zhirong Liu, Zhenhua Dong, Jiebo Luo, Philip S. Yu.
    ACM/IEEE ASONAM. 2019.
    [Paper][Slides][English Blog][BibTeX]

  • A Review of Recent Advance in Online Spam Detection.
    Yingtong Dou.
    Technical Report. Mar. 2019.
    [Paper][Slides][BibTeX]

  • A Novel Centrality Cascading Based Edge Parameter Evaluation Method for Robust Influence Maximization.
    Xiaolong Deng, Yingtong Dou, Tiejun Lv, Nguyen QVH.
    IEEE Access. 2017.
    [Paper][Code][Slides][BibTeX]

  • 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]

Projects

  • Misinformation Detection

projects4 Introduction We investigate various problems and challenges regarding fact-checking and fake news classification tasks. Some of the problems are: user endogeneous preference encoding, zero/few-shot fake news detection, and fake news detection under adversarial settings.

Resources Project Homepage. A collection of GNN-based fake news detectors and two fake news propagation graph datasets. Benchmarking GNN-based fake news detection.


  • Robust Fraud Detection

projects3 Introduction The adversarial behaviors between advanced spammers and the defenders make the fraud detection problem more challenging. We employ various machine learning methods to simulate the adversarial behavior between two sides and devise robust fraud detectors.

Resources Project Homepage. A curated list of up-to-date papers on fraud detection. Deep and Non-deep Graph-based Toolboxes for Fraud Detection. Introduction Slides


  • Securing Graph-based Learning Models

projects2 Introduction Despite the advance of graph-based learning models like probabilistic graphical models and graph neural networks, their applications to various areas also face diverse threats. We investigate the practical threats of SOTA models and secure them from multiple channels.

Resources A survey from our lab on adversarial attack and defense on graph data. A list of papers on graph adversarial learning.


  • Suspicious Behavior Modeling in Mobile App Markets

projects1 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 blog post about download fraud in App markets.