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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |