Self-supervised Graph Representation Learning for Black Market Account Detection

TL;DR

This paper presents SGRL, a self-supervised graph learning system tailored for detecting black market accounts in WeChat, outperforming existing methods in both offline and online evaluations.

Contribution

The paper introduces a novel self-supervised graph neural network approach specifically designed for black market account detection in large-scale messaging platforms.

Findings

SGRL outperforms state-of-the-art methods by 16.06%-58.17% offline.

SGRL exceeds alternative methods by 7.27% online.

Effective in large-scale, real-world deployment with minimal label reliance.

Abstract

Nowadays, Multi-purpose Messaging Mobile App (MMMA) has become increasingly prevalent. MMMAs attract fraudsters and some cybercriminals provide support for frauds via black market accounts (BMAs). Compared to fraudsters, BMAs are not directly involved in frauds and are more difficult to detect. This paper illustrates our BMA detection system SGRL (Self-supervised Graph Representation Learning) used in WeChat, a representative MMMA with over a billion users. We tailor Graph Neural Network and Graph Self-supervised Learning in SGRL for BMA detection. The workflow of SGRL contains a pretraining phase that utilizes structural information, node attribute information and available human knowledge, and a lightweight detection phase. In offline experiments, SGRL outperforms state-of-the-art methods by 16.06%-58.17% on offline evaluation measures. We deploy SGRL in the online environment to detect BMAs on the billion-scale WeChat graph, and it exceeds the alternative by 7.27% on the online evaluation measure. In conclusion, SGRL can alleviate label reliance, generalize well to unseen data, and effectively detect BMAs in WeChat.