Heterogeneous Graph Neural Networks for Malicious Account Detection

Authors: Ziqi Liu, Chaochao Chen, Xinxing Yang, Jun Zhou, Xiaolong Li, Le Song
Published: 2020-02-27

Source: https://arxiv.org/abs/2002.12307

PDF: https://arxiv.org/pdf/2002.12307

Labels Predicted by AI

GNN 機械学習手法 グラフプライバシー

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world’s leading mobile cashless payment platform. Our approach, inspired from a connected subgraph approach, adaptively learns discriminative embeddings from heterogeneous account-device graphs based on two fundamental weaknesses of attackers, i.e. device aggregation and activity aggregation. For the heterogeneous graph consists of various types of nodes, we propose an attention mechanism to learn the importance of different types of nodes, while using the sum operator for modeling the aggregation patterns of nodes in each type. Experiments show that our approaches consistently perform promising results compared with competitive methods over time.