An improve fraud detection framework via dynamic representations and adaptive frequency response filter

Abstract The evolution of telecommunication technologies not only enhances social interactions but also inadvertently fosters an environment for telecom fraud. Graph-like data generated from traceable telecommunication interactions offers a foundation for graph-based fraud detection. However, the co...

Full description

Saved in:
Bibliographic Details
Main Authors: Juncheng Yang, Shuxia Li, Zijun Huang, Junhang Wu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-02032-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688146082529280
author Juncheng Yang
Shuxia Li
Zijun Huang
Junhang Wu
author_facet Juncheng Yang
Shuxia Li
Zijun Huang
Junhang Wu
author_sort Juncheng Yang
collection DOAJ
description Abstract The evolution of telecommunication technologies not only enhances social interactions but also inadvertently fosters an environment for telecom fraud. Graph-like data generated from traceable telecommunication interactions offers a foundation for graph-based fraud detection. However, the complexity and dynamism of interaction networks present formidable challenges. Our data exploration revealed that fraudsters exhibit consistent distinguishability from normal users in specific dynamic behavioral traits. Leveraging previous research, we constructed a latent synergy network (LSN) through second-order relations. Analysis of LSN exposed that fraudsters, seeking to elude detection, adopt deceptive behaviors by establishing connections with numerous normal users, leading to the over-smoothing problem in traditional GNN models. Consequently, we introduce the Dynamic Pattern with Adaptive Filter Graph Learning framework for telecom fraud detection. With the sequential network, we capture users’ dynamic behavioral features for LSN input. Additionally, in LSN learning, we designed a trainable filter to capture differences between feature channels during information aggregation, mitigating the over-smoothing problem. On the Sichuan Telecom, Sichuan-mini Telecom, and YelpChi datasets, using AUC, Recall, and F1-score as evaluation metrics, DPGFD outperforms GCN, GraphSAGE, FRAUDRE, BWGNN, and GAGA by an average of 5%.
format Article
id doaj-art-36bb36925ecb4d6bae1c163abe5c09e6
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-36bb36925ecb4d6bae1c163abe5c09e62025-08-20T03:22:07ZengNature PortfolioScientific Reports2045-23222025-05-0115111410.1038/s41598-025-02032-9An improve fraud detection framework via dynamic representations and adaptive frequency response filterJuncheng Yang0Shuxia Li1Zijun Huang2Junhang Wu3School of Electronic Information Engineering, Henan Polytechnic InstituteSchool of Electronic Information Engineering, Henan Polytechnic InstituteSchool of Computer Science, Wuhan UniversitySchool of Computer Science, Wuhan UniversityAbstract The evolution of telecommunication technologies not only enhances social interactions but also inadvertently fosters an environment for telecom fraud. Graph-like data generated from traceable telecommunication interactions offers a foundation for graph-based fraud detection. However, the complexity and dynamism of interaction networks present formidable challenges. Our data exploration revealed that fraudsters exhibit consistent distinguishability from normal users in specific dynamic behavioral traits. Leveraging previous research, we constructed a latent synergy network (LSN) through second-order relations. Analysis of LSN exposed that fraudsters, seeking to elude detection, adopt deceptive behaviors by establishing connections with numerous normal users, leading to the over-smoothing problem in traditional GNN models. Consequently, we introduce the Dynamic Pattern with Adaptive Filter Graph Learning framework for telecom fraud detection. With the sequential network, we capture users’ dynamic behavioral features for LSN input. Additionally, in LSN learning, we designed a trainable filter to capture differences between feature channels during information aggregation, mitigating the over-smoothing problem. On the Sichuan Telecom, Sichuan-mini Telecom, and YelpChi datasets, using AUC, Recall, and F1-score as evaluation metrics, DPGFD outperforms GCN, GraphSAGE, FRAUDRE, BWGNN, and GAGA by an average of 5%.https://doi.org/10.1038/s41598-025-02032-9
spellingShingle Juncheng Yang
Shuxia Li
Zijun Huang
Junhang Wu
An improve fraud detection framework via dynamic representations and adaptive frequency response filter
Scientific Reports
title An improve fraud detection framework via dynamic representations and adaptive frequency response filter
title_full An improve fraud detection framework via dynamic representations and adaptive frequency response filter
title_fullStr An improve fraud detection framework via dynamic representations and adaptive frequency response filter
title_full_unstemmed An improve fraud detection framework via dynamic representations and adaptive frequency response filter
title_short An improve fraud detection framework via dynamic representations and adaptive frequency response filter
title_sort improve fraud detection framework via dynamic representations and adaptive frequency response filter
url https://doi.org/10.1038/s41598-025-02032-9
work_keys_str_mv AT junchengyang animprovefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT shuxiali animprovefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT zijunhuang animprovefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT junhangwu animprovefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT junchengyang improvefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT shuxiali improvefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT zijunhuang improvefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter
AT junhangwu improvefrauddetectionframeworkviadynamicrepresentationsandadaptivefrequencyresponsefilter