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

TL;DR

IMBWatch is a novel spatio-temporal graph neural network framework that effectively detects illicit massage businesses by analyzing dynamic online and offline data patterns, outperforming existing methods in accuracy and interpretability.

Contribution

The paper introduces IMBWatch, a scalable ST-GNN approach that models complex spatio-temporal patterns in illicit massage business networks using heterogeneous data sources.

Findings

IMBWatch achieves higher accuracy and F1 scores than baseline models.

The framework provides actionable insights for targeted interventions.

IMBWatch is scalable and adaptable to other illicit activity detection tasks.

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.