EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DriftShield: Autonomous Fraud Detection via Actor-Critic Reinforcement Learning With Dynamic Feature Reweighting

Jialei Cao, Wenxia Zheng, Yao Ge, Jiyuan Wang

IEEE Open Journal of the Computer Society · 2025 · 6 · 1166-1177

DOI: 10.1109/ojcs.2025.3587001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of the Computer Society, 2025. Verfasst von Jialei Cao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Financial fraud detection systems confront the persistent challenge of concept drift, where fraudulent patterns evolve continuously to evade detection mechanisms. Traditional rule-based methods and static machine learning models require frequent manual updates, failing to autonomously adapt to emerging fraud strategies. This article presents DriftShield, a novel adaptive fraud detection framework that addresses these limitations through four key technical innovations: (1) the first application of Soft Actor-Critic (SAC) reinforcement learning with continuous action spaces to fraud detection, enabling simultaneous fine-grained optimization of detection thresholds and feature importance weights; (2) a dynamic feature reweighting mechanism that automatically adapts to evolving fraud patterns while providing interpretable insights into changing fraud strategies; (3) an adaptive experience replay buffer combining sliding windows with prioritized sampling to balance catastrophic forgetting prevention with rapid concept drift adaptation; and (4) an entropy-driven exploration framework with automatic temperature tuning that intelligently balances exploitation of known fraud patterns with discovery of emerging threats. Experimental evaluation demonstrates that DriftShield achieves 18% higher fraud detection rates while maintaining lower false positive rates compared to static models. The system demonstrates 57% faster adaptation times, recovering optimal performance within 280 transactions after significant concept drift compared to 650 transactions for the next-best reinforcement learning approach. DriftShield attains a cumulative detection rate of 0.849, representing a 7.7% improvement over existing methods and establishing the efficacy of continuous-action reinforcement learning for autonomous adaptation in dynamic adversarial environments.

Zitieren

APA

Cao, J., Zheng, W., Ge, Y., & Wang, J. (2025). DriftShield: Autonomous Fraud Detection via Actor-Critic Reinforcement Learning With Dynamic Feature Reweighting. IEEE Open Journal of the Computer Society, 6, 1166-1177. https://doi.org/10.1109/ojcs.2025.3587001

Vancouver

Cao J, Zheng W, Ge Y, Wang J. DriftShield: Autonomous Fraud Detection via Actor-Critic Reinforcement Learning With Dynamic Feature Reweighting. IEEE Open Journal of the Computer Society. 2025;6:1166-1177. doi:10.1109/ojcs.2025.3587001

BibTeX
@article{Cao2025,
  author = {Cao, Jialei and Zheng, Wenxia and Ge, Yao and Wang, Jiyuan},
  title = {DriftShield: Autonomous Fraud Detection via Actor-Critic Reinforcement Learning With Dynamic Feature Reweighting},
  journal = {IEEE Open Journal of the Computer Society},
  year = {2025},
  volume = {6},
  pages = {1166--1177},
  doi = {10.1109/ojcs.2025.3587001}
}
Kostenlos starten →