Scholarlink

<p>The rapid growth of mobile networks has enhanced social interactions but has also increased fraud risks in mobile social networks, leading to financial and economic losses. Fraud detection systems based on Graph Neural Networks (GNNs) utilize Call Detail Record (CDR) data to analyze social behaviors, yet they struggle with data imbalance, which limits their effectiveness. In this study, we address this challenge by developing an improved minority class data augmentation approach for graph-based fraud detection. Building upon existing generative models, we enhance data generation using Wasserstein GAN with Gradient Penalty (WGAN-GP) to mitigate mode collapse and Deep Denoising Diffusion Models (DDPM) to generate high-quality synthetic data. These synthetic samples are then integrated with graph-based classifiers to improve fraud detection performance. Experimental results demonstrate that our approach significantly improves classification performance, particularly in terms of F1-score, recall, and generalization across multiple graph-based fraud detection models. This research contributes to advancing data augmentation techniques for imbalanced graph data, ultimately enhancing fraud detection effectiveness and network security in mobile telecommunications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fraud calls detection using class-imbalanced learning on graph structures

  • 期刊论文

  • 发表日期：

    2025年5月1日

查看全文
  • Nguyen Tan Cam,
  • Dinh Hoai Hiep

摘要

The rapid growth of mobile networks has enhanced social interactions but has also increased fraud risks in mobile social networks, leading to financial and economic losses. Fraud detection systems based on Graph Neural Networks (GNNs) utilize Call Detail Record (CDR) data to analyze social behaviors, yet they struggle with data imbalance, which limits their effectiveness. In this study, we address this challenge by developing an improved minority class data augmentation approach for graph-based fraud detection. Building upon existing generative models, we enhance data generation using Wasserstein GAN with Gradient Penalty (WGAN-GP) to mitigate mode collapse and Deep Denoising Diffusion Models (DDPM) to generate high-quality synthetic data. These synthetic samples are then integrated with graph-based classifiers to improve fraud detection performance. Experimental results demonstrate that our approach significantly improves classification performance, particularly in terms of F1-score, recall, and generalization across multiple graph-based fraud detection models. This research contributes to advancing data augmentation techniques for imbalanced graph data, ultimately enhancing fraud detection effectiveness and network security in mobile telecommunications.