A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910052427759616 |
|---|---|
| author | Ismail, Nasim Abdirahman Karaarslan, Enis |
| author_facet | Ismail, Nasim Abdirahman Karaarslan, Enis |
| contents | High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based and discriminative models struggle with "zero-day" attacks due to extreme class imbalance and the lack of historical precedents. This paper proposes a Dual-Path Generative Framework that decouples real-time anomaly detection from offline adversarial training. The architecture employs a Variational Autoencoder (VAE) to establish a legitimate transaction manifold based on reconstruction error, ensuring <50ms inference latency. In parallel, an asynchronous Wasserstein GAN with Gradient Penalty (WGAN-GP) synthesizes high-entropy fraudulent scenarios to stress-test the detection boundaries. Crucially, to address the non-differentiability of discrete banking data (e.g., Merchant Category Codes), we integrate a Gumbel-Softmax estimator. Furthermore, we introduce a trigger-based explainability mechanism where SHAP (Shapley Additive Explanations) is activated only for high-uncertainty transactions, reconciling the computational cost of XAI with real-time throughput requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13237 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems Ismail, Nasim Abdirahman Karaarslan, Enis Artificial Intelligence Cryptography and Security 68T07 I.2.6; K.6.5; J.1 High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based and discriminative models struggle with "zero-day" attacks due to extreme class imbalance and the lack of historical precedents. This paper proposes a Dual-Path Generative Framework that decouples real-time anomaly detection from offline adversarial training. The architecture employs a Variational Autoencoder (VAE) to establish a legitimate transaction manifold based on reconstruction error, ensuring <50ms inference latency. In parallel, an asynchronous Wasserstein GAN with Gradient Penalty (WGAN-GP) synthesizes high-entropy fraudulent scenarios to stress-test the detection boundaries. Crucially, to address the non-differentiability of discrete banking data (e.g., Merchant Category Codes), we integrate a Gumbel-Softmax estimator. Furthermore, we introduce a trigger-based explainability mechanism where SHAP (Shapley Additive Explanations) is activated only for high-uncertainty transactions, reconciling the computational cost of XAI with real-time throughput requirements. |
| title | A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems |
| topic | Artificial Intelligence Cryptography and Security 68T07 I.2.6; K.6.5; J.1 |
| url | https://arxiv.org/abs/2603.13237 |