EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GDFGAT: Graph attention network based on feature difference weight assignment for telecom fraud detection

An Tong iD, Bochao Chen iD, Zhe Wang iD, Jiawei Gao iD, Chi Kin Lam iD

PLOS One · 30.05.2025 · 20 (5) · e0322004

DOI: 10.1371/journal.pone.0322004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 30.05.2025. Verfasst von An Tong und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Applied Sciences, Macao Polytechnic University, Macao, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Fraud, Telecommunications. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the number of telecom frauds has increased significantly, causing substantial losses to people’s daily lives. With technological advancements, telecom fraud methods have also become more sophisticated, making fraudsters harder to detect as they often imitate normal users and exhibit highly similar features. Traditional graph neural network (GNN) methods aggregate the features of neighboring nodes, which makes it difficult to distinguish between fraudsters and normal users when their features are highly similar. To address this issue, we proposed a spatio-temporal graph attention network (GDFGAT) with feature difference-based weight updates. We conducted comprehensive experiments on our method on a real telecom fraud dataset. Our method obtained an accuracy of 93.28%, f1 score of 92.08%, precision rate of 93.51%, recall rate of 90.97%, and AUC value of 94.53%. The results showed that our method (GDFGAT) is better than the classical method, the latest methods and the baseline model in many metrics; each metric improved by nearly 2%. In addition, we also conducted experiments on the imbalanced datasets: Amazon and YelpChi. The results showed that our model GDFGAT performed better than the baseline model in some metrics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerFraudTelecommunicationsHumansAlgorithms

Autor:innen und Institutionen

  • Faculty of Applied Sciences, Macao Polytechnic University, Macao, China.

ORCID-Profile: An Tong, Bochao Chen, Zhe Wang, Jiawei Gao, Chi Kin Lam

Zitieren

APA

Tong, A., Chen, B., Wang, Z., Gao, J., & Lam, C. K. (2025). GDFGAT: Graph attention network based on feature difference weight assignment for telecom fraud detection. PLOS One, 20(5), e0322004. https://doi.org/10.1371/journal.pone.0322004

Vancouver

Tong A, Chen B, Wang Z, Gao J, Lam CK. GDFGAT: Graph attention network based on feature difference weight assignment for telecom fraud detection. PLOS One. 2025;20(5):e0322004. doi:10.1371/journal.pone.0322004

BibTeX
@article{Tong2025,
  author = {Tong, An and Chen, Bochao and Wang, Zhe and Gao, Jiawei and Lam, Chi Kin},
  title = {GDFGAT: Graph attention network based on feature difference weight assignment for telecom fraud detection},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {5},
  pages = {e0322004},
  doi = {10.1371/journal.pone.0322004}
}
Kostenlos starten →