Privacy-Preserving Behavioral Anomaly Detection in Dynamic Graphs for Card Transactions - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

Privacy-Preserving Behavioral Anomaly Detection in Dynamic Graphs for Card Transactions

Résumé

Anomaly detection in financial transactions poses significant privacy challenges. This paper introduces a federated learning (FL) framework for Privacy-Preserving Behavioral Anomaly Detection using Graph Neural Networks (GNNs) on dynamic graphs to model cardholder transactions. We incorporate anonymization-based and noise-based privacypreserving methods for feature engineering and a domain-specific negative sampling technique to train models without labeled data, making it suitable for real-world applications. Our results, benchmarked on synthetic and real-world datasets, show that deep learning-based outperform clustering-based methods, with F1-scores of 0.91±0.02 and 0.87±0.04, respectively. Additionally, using the anomaly score as a feature in fraud detection models yields a 1.76%±0.54% improvement in F1-score, enhancing fraud detection performance while preserving privacy.

Fichier principal
Vignette du fichier
Paper_WISE2024.pdf (588.67 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04707065 , version 1 (24-09-2024)

Identifiants

  • HAL Id : hal-04707065 , version 1

Citer

Farouk Damoun, Hamida Seba, Radu State. Privacy-Preserving Behavioral Anomaly Detection in Dynamic Graphs for Card Transactions. 2024. ⟨hal-04707065⟩
0 Consultations
0 Téléchargements

Partager

More