Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control

• URL: http://arxiv.org/abs/2609.14234v1
• Date: Sun, 13 Sep 2026 01:56:22 GMT
• Title: Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control
• Abstract summary: GTFD fuses structural and temporal evidence from a corporation's payment graph.<n>It reduces the false-positive rate by about 29% relative to the strongest baseline.<n>It retains 89.2% accuracy at perturbation magnitude 0.20 where the next-best model falls to 76.4%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Financial fraud in corporate transaction networks has grown more coordinated and harder to detect with rule-based engines and with classical learning models that treat each transaction in isolation. This paper presents GTFD, a graph-transformer fraud detector that fuses structural and temporal evidence from a corporation's payment graph. GTFD encodes the graph with a multi-head graph attention network, encodes ordered transaction sequences with a gated transformer, and combines both views through a cross-modal gating layer. A conformal risk-control head converts the fused representation into threshold-free anomaly scores with finite-sample coverage guarantees, and the network is trained with self-supervised link-mask pretraining plus adversarial augmentation so it remains stable under scarce labels and under adversarial perturbation. On a corporate transaction benchmark enriched with coordinated fraud rings, GTFD reaches an AUROC of 0.990, an F1-score of 96.1% (precision 96.3%, recall 95.9%), and an accuracy of 98.4%. It reduces the false-positive rate by about 29% relative to the strongest baseline while raising coordinated fraud-ring recall from 85.1% to 96.5%. Ablations attribute roughly 2.0 AUROC points to self-supervised pretraining and 1.9 AUROC points to the conformal head, and adversarial stress tests show GTFD retains 89.2% accuracy at perturbation magnitude 0.20 where the next-best model falls to 76.4%.

Related papers

• Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G [90.42669277637026]
  Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence.<n>This article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks.
  arXiv  Detail & Related papers  (2026-09-09T01:36:44Z)
• ChequeMark: An Ensemble Machine Learning Framework for After-Hours Business Deposit Fraud Detection [4.847320494918926]
  Cheque fraud is a material risk in after-hours business deposit operations because funds may be released within one business day, while cheque clearing takes several days.<n>We propose a multi-view ensemble ML framework that combines: Extreme Gradient Boosting (XGBoost) for known fraud patterns, Isolation Forest for label-free anomaly detection, and Graph Sample and Aggregate (GraphSAGE) for relational patterns associated with transaction activities.
  arXiv  Detail & Related papers  (2026-08-21T21:00:41Z)
• Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion [9.298391210599604]
  In our CSI300 setting, only $sim$80 positive samples are observed across 791 training days, making heavily supervised multi-source models unstable.<n>We propose textbfAAMSF (Anomaly-Augmented Multi-Signal Fusion), a semisupervised framework that combines anomaly scores over market indicators, GDELT events, Chinese financial news, and English media with lightweight Ridge score fusion.<n>On CSI300, AAMSF achieves test AUC-ROC textbf0.680, outperforming the strongest unsupervised baseline (0.630) and neural baseline (0.588
  arXiv  Detail & Related papers  (2026-07-26T14:30:58Z)
• An AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts [0.0]
  Banks simultaneously face signature-based fraud and behavioural financial crime.<n> Static rule engines that reliably catch brute-force and high-velocity events are structurally blind to business-email-compromise.<n>This paper presents an AI security agent for retail and corporate banking that addresses this gap.
  arXiv  Detail & Related papers  (2026-06-16T05:58:40Z)
• An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks [0.0]
  This paper evaluates the performance of AI-driven models for fraud detection in telecommunication networks.<n>The Telecom CDR dataset contains 101,174 customer records with 17 attributes, including 8,830 fraud cases.<n>RF was seen to give the highest performance with an accuracy of 99.9% and precision of 99.9%.
  arXiv  Detail & Related papers  (2026-05-17T04:03:36Z)
• Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning [42.558423984270135]
  Federated Learning (FL) enables the training of machine learning models across decentralized clients while preserving data privacy.<n>The presence of anomalous or corrupted clients can significantly degrade model performance.<n>We propose WAFFLE a detection algorithm that labels malicious clients it before training<n>A lightweight detector, trained on a distillated public dataset, performs the labeling with minimal communication and computational overhead.
  arXiv  Detail & Related papers  (2025-06-11T12:48:00Z)
• A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection [60.09453163562244]
  We propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD.<n>In the estimation module, we design a novel label-free heterophily metric called HALO, which captures the critical graph properties for GFD.<n>In the alignment-based fraud detection module, we develop a joint-GNN architecture with ranking loss and asymmetric alignment loss.
  arXiv  Detail & Related papers  (2025-02-18T22:07:36Z)
• Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation [28.745101225936697]
  We propose a semi-supervised graph neural network for fraud detection.<n>Specifically, we leverage transaction records to construct a temporal transaction graph.<n>We then pass messages among the nodes through a Gated Temporal Attention Network (GTAN) to learn the transaction representation.
  arXiv  Detail & Related papers  (2024-12-24T08:48:48Z)
• Securing Transactions: A Hybrid Dependable Ensemble Machine Learning Model using IHT-LR and Grid Search [2.4374097382908477]
  We introduce a state-of-the-art hybrid ensemble (ENS) Machine learning (ML) model that intelligently combines multiple algorithms to enhance fraud identification. Our experiments are conducted on a publicly available credit card dataset comprising 284,807 transactions. The proposed model achieves impressive accuracy rates of 99.66%, 99.73%, 98.56%, and 99.79%, and a perfect 100% for the DT, RF, KNN, and ENS models, respectively.
  arXiv  Detail & Related papers  (2024-02-22T09:01:42Z)
• Transaction Fraud Detection via an Adaptive Graph Neural Network [64.9428588496749]
  We propose an Adaptive Sampling and Aggregation-based Graph Neural Network (ASA-GNN) that learns discriminative representations to improve the performance of transaction fraud detection. A neighbor sampling strategy is performed to filter noisy nodes and supplement information for fraudulent nodes. Experiments on three real financial datasets demonstrate that the proposed method ASA-GNN outperforms state-of-the-art ones.
  arXiv  Detail & Related papers  (2023-07-11T07:48:39Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.