Dr DriftGuard-HCL is presented, a continual heterogeneous graph-contrastive framework that combines a scalable typed graph-context encoder, semantic-group contrastive regularization, delayed-label replay, and a relation-support-aware drift gate to support the value of drift-gated adaptation while not constituting evidence of production-bank performance.
This paper proposes ATGNN-SP, a drift-gated stable-plastic temporal graph neural network for real-time-compatible fraud scoring, a drift-gated stable-plastic temporal graph neural network for real-time-compatible fraud scoring.
Xin-Ran Yue, Jing-Yun Yang, Ru-Feng Zhu et al.· Highlights in Business, Econ...· 0 citations
Email communication remains the primary vector for sophisticated cyber threats, including phishing and spam, resulting in billions of dollars in annual financial losses. While state-of-the-art deep learning (DL) models have demonstrated high precision in static environments, they frequently suffer from performance degr...
Mohammed Abdulwahab, Muneer Almekhlafi, Raeed Al-Sabri· 2026 6th International Confe...· 0 citations
Financial fraud detection is increasingly challenged by concept drift, evolving transaction behaviour, and adversarial adaptation, which can degrade conventional anomaly-detection methods under distributional change. Although unsupervised anomaly detection is widely used because labelled fraud data are scarce, most a...
Francis Thiong'o, Lawrence Nderu, R. Mwangi et al.· Scientific Reports· 0 citations
This work views delayed residuals as compressed observations of latent drift over the horizon, and proposes PADRE, a drift evidence driven framework that converts each delayed feedback event into a context-sensitive adaptation decision, and builds a Tri-View drift representation.
Xing-Wang Li, Fei Teng, Cong Zhou et al.· Proceedings of the Thirty-Fi...· 1 citation
A multi-view ensemble ML framework that combines Extreme Gradient Boosting for known fraud patterns, Isolation Forest for label-free anomaly detection, and Graph Sample and Aggregate for relational patterns associated with transaction activities is proposed.
Digital ad fraud continuously evolves through device spoofing, behavior simulation, and coordinated traffic attacks, making the detection of sophisticated fraudulent activities a persistent challenge. In real-world settings, only a small fraction of fraudulent traffic receives reliable labels, while vast amounts of unl...
Li-Fei Wei, Weifan Yang, Yan Meng et al.· Algorithms· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
