Team Members: Steph Buongiorno
To make the response to human trafficking more resilient, we propose the development of a new data ecosystem based on open knowledge networks (OKNs) combined with AI-driven information retrieval technology to improve data accessibility for diverse stakeholders. Focusing on Texas, our research will address the challenges of creating a distributed OKN that holds sensitive information, which cannot be shared directly.
The ecosystem will initially be anchored by SMU’s Human Trafficking Data Warehouse, with support from the National Institute of Justice (NIJ). In this phase, we will design and develop a scalable, AI agent-based OKN architecture to facilitate information flow between stakeholders such as researchers, law enforcement, DHS, and travel intermediaries. This system will enable users to input knowledge artifacts and interact with an AI-driven interface that leverages the OKN to automatically identify relevant data and techniques to answer their queries. Our goal is to improve the information exchange between these stakeholders while adhering to legal standards and minimizing the risks to individual and societal harm, safeguarding civil rights, and protecting marginalized populations.
The OKN will feature four types of AI agents—Bridging Agents to secure data connections, Analyst Agents, Visualization Agents, and Integrity Agents responsible for validating privacy and data sharing policies. A validation loop will be incorporated, allowing agents to mediate input and output data in compliance with privacy regulations, with human oversight providing additional validation and authorization.