English

Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA Graph

Social and Information Networks 2024-04-05 v2 Artificial Intelligence

Abstract

The rise of the click farm business using Multi-purpose Messaging Mobile Apps (MMMAs) tempts cybercriminals to perpetrate crowdsourcing frauds that cause financial losses to click farm workers. In this paper, we propose a novel contrastive multi-view learning method named CMT for crowdsourcing fraud detection over the heterogeneous temporal graph (HTG) of MMMA. CMT captures both heterogeneity and dynamics of HTG and generates high-quality representations for crowdsourcing fraud detection in a self-supervised manner. We deploy CMT to detect crowdsourcing frauds on an industry-size HTG of a representative MMMA WeChat and it significantly outperforms other methods. CMT also shows promising results for fraud detection on a large-scale public financial HTG, indicating that it can be applied in other graph anomaly detection tasks. We provide our implementation at https://github.com/KDEGroup/CMT.

Keywords

Cite

@article{arxiv.2308.02793,
  title  = {Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA Graph},
  author = {Zequan Xu and Qihang Sun and Shaofeng Hu and Jieming Shi and Hui Li},
  journal= {arXiv preprint arXiv:2308.02793},
  year   = {2024}
}

Comments

Full technical report for our DASFAA 2024 paper: Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA Graph

R2 v1 2026-06-28T11:48:46.029Z