Suspicious: a Resilient Semi-Supervised Framework for Graph Fraud Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Suspicious: a Resilient Semi-Supervised Framework for Graph Fraud Detection

Baptiste Jeudy
Christine Largeron
Damien Saboul
  • Fonction : Auteur
  • PersonId : 1353200

Résumé

Graph-based fraud detection is an important task in many real-world domains such as insurance, finance, and cybersecurity. Even if existing semi-supervised models have proven to be efficient in identifying anomalous nodes, they assume that a labeled sample of the nodes is available to train the model, without taking into account the real-world problem of the unreliability of such a sample. In practice, the labeling is often done manually and contains many errors. In this paper, we study fraud detection in attributed networks, and we propose a new framework, based on two graph auto-encoders trained following a suspicion mechanism: the first auto-encoder is trained to better reconstruct the normal nodes while the second one, the fraudulent ones. The final classification is done by coupling the result of both auto-encoders. We demonstrate that our approach obtains at least equivalent performances to state of the art methods in the case of a perfectly labeled sample while being more resilient to the introduction of mistakes in this sample.
Fichier principal
Vignette du fichier
Suspicious_ICTAI-8.pdf (844.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04461200 , version 1 (16-02-2024)

Identifiants

Citer

Bastien Giles, Baptiste Jeudy, Christine Largeron, Damien Saboul. Suspicious: a Resilient Semi-Supervised Framework for Graph Fraud Detection. 35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Nov 2023, Atlanta, GA, United States. pp.212-220, ⟨10.1109/ictai59109.2023.00039⟩. ⟨hal-04461200⟩
6 Consultations
15 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More