Leveraging Graph Neural Networks and Anomaly Detection to Deconstruct Terrorist Financing Networks in Nigeria’s Emerging Cryptocurrency Ecosystem

Domaine:

peace and securitydigital infrastructure

Type de record:

paper

Créateur:

CenYus

Éditeur:

Way

Hôte:

The proliferation of cryptocurrency markets in Nigeria presents a complex challenge for national security. It offers new avenues for terrorist organizations to obscure financial transactions. Traditional regulatory and financial surveillance methods are ill-equipped to analyze the pseudo-anonymous, high-volume, and non-linear transaction graphs inherent in blockchain economies. This pioneering study proposes a novel AI-driven framework to assess terrorism financing (TF) risks. The study utilized Graph Neural Networks (GNNs) to model the Nigerian cryptocurrency transaction landscape, mapping flow patterns and identifying latent network structures. Superimposed on this graph, an ensemble of unsupervised anomaly detection models, including Isolation Forests and Autoencoders, is deployed to flag high-risk transaction clusters and behavioral outliers. Our research pioneers a method to move beyond simplistic transaction monitoring to a holistic network-level risk assessment. The findings demonstrate AI’s capacity to deconstruct emerging TF typologies in real-time, offering a paradigm shift from reactive compliance to proactive intelligence-led disruption. We conclude by critically evaluating this AI framework against the nascent regulatory responses in Nigeria, proposing a synergistic model where adaptive AI tools can inform and future-proof financial policy.

Visit

doi.org

Similaires

Arabic fake news detection using graph neural networks with heterogeneous graphOrbit-Equivariant Graph Neural NetworksLeveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty MappingPredicting Nigeria’s petroleum price: A comparison between recurrent neural networks, multilayer perceptron neural networks, and generalized regression neural networksGraph Neural Networks for end-to-end information extraction from handwritten documentsOptimizing Anomaly Detection in 5G and Beyond Networks using Reinforcement Learning

Arabic fake news detection using graph neural networks with heterogeneous graph

Detecting and fighting fake news is vital in the digital age, preventing the dissemination of false

Orbit-Equivariant Graph Neural Networks

Orbit-Equivariant Graph Neural Networks

Poster presented at the Deep Learning Indaba 2023 by Matthew Morris

Leveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mapping

Accurate, fine-grained poverty maps remain scarce across much of the Global South. While Demographic

Predicting Nigeria’s petroleum price: A comparison between recurrent neural networks, multilayer perceptron neural networks, and generalized regression neural networks

Predicting petroleum pump prices assists in knowing when, how, and what quality to purchase. The pur

Graph Neural Networks for end-to-end information extraction from handwritten documents

Graph Neural Networks for end-to-end information extraction from handwritten documents

Poster presented at the Deep Learning Indaba 2023 by yessine khanfir

Optimizing Anomaly Detection in 5G and Beyond Networks using Reinforcement Learning

Kenya has experienced significant growth in internet use and adoption, evidenced by the rapid deploy