Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA Graph
It addresses financial losses for click farm workers by detecting fraud in multi-purpose messaging mobile apps, with incremental improvements in graph anomaly detection.
The paper tackles crowdsourcing fraud detection on heterogeneous temporal graphs, proposing a contrastive multi-view learning method (CMT) that significantly outperforms other methods on an industry-size WeChat dataset and shows promising results on a public financial graph.
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.