IMBWatch -- a Spatio-Temporal Graph Neural Network approach to detect Illicit Massage Business

2025-12-31

AI Summary

This study addresses the challenge of detecting illicit massage businesses (IMBs), whose covert operations evade conventional identification methods. To this end, we propose a spatiotemporal graph neural network model based on dynamic heterogeneous graphs that integrates multi-source open-source intelligence—including advertisements, business licenses, and user reviews—to capture the evolving spatiotemporal relationships among heterogeneous entities such as establishments, aliases, phone numbers, and addresses. By incorporating a spatiotemporal attention mechanism, our approach represents the first application of graph neural networks to IMB detection, effectively uncovering concealed behaviors like cross-city personnel movement and disposable phone number rotation, while also offering interpretability. Evaluated on real-world datasets from multiple U.S. cities, the model significantly outperforms baseline methods in both accuracy and F1 score, enabling scalable and reproducible research against illicit activities.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Illicit Massage Businesses (IMBs) are a covert and persistent form of organized exploitation that operate under the facade of legitimate wellness services while facilitating human trafficking, sexual exploitation, and coerced labor. Detecting IMBs is difficult due to encoded digital advertisements, frequent changes in personnel and locations, and the reuse of shared infrastructure such as phone numbers and addresses. Traditional approaches, including community tips and regulatory inspections, are largely reactive and ineffective at revealing the broader operational networks traffickers rely on. To address these challenges, we introduce IMBWatch, a spatio-temporal graph neural network (ST-GNN) framework for large-scale IMB detection. IMBWatch constructs dynamic graphs from open-source intelligence, including scraped online advertisements, business license records, and crowdsourced reviews. Nodes represent heterogeneous entities such as businesses, aliases, phone numbers, and locations, while edges capture spatio-temporal and relational patterns, including co-location, repeated phone usage, and synchronized advertising. The framework combines graph convolutional operations with temporal attention mechanisms to model the evolution of IMB networks over time and space, capturing patterns such as intercity worker movement, burner phone rotation, and coordinated advertising surges. Experiments on real-world datasets from multiple U.S. cities show that IMBWatch outperforms baseline models, achieving higher accuracy and F1 scores. Beyond performance gains, IMBWatch offers improved interpretability, providing actionable insights to support proactive and targeted interventions. The framework is scalable, adaptable to other illicit domains, and released with anonymized data and open-source code to support reproducible research.

Problem

• Illicit Massage Business
• human trafficking
• spatio-temporal graph
• exploitation
• covert operations

Innovation

• Spatio-Temporal Graph Neural Network
• Illicit Massage Business Detection
• Dynamic Heterogeneous Graph
• Temporal Attention Mechanism
• Open-Source Intelligence