Research Program
Trustworthy, Resilient, and Secure Intelligent Systems
Artificial intelligence is rapidly evolving from isolated predictive models into interconnected systems operating across organizations, networks, scientific infrastructure, and autonomous environments. As these systems exchange information, retrieve external knowledge, invoke software tools, and make increasingly autonomous decisions, accuracy alone is insufficient. They must also remain secure, privacy-preserving, resilient, explainable, and accountable when their data, users, or computational environments cannot always be trusted. The TRUST Systems Lab conducts research at the intersection of artificial intelligence, machine learning, cybersecurity, and distributed intelligent systems.
Research Thrusts
Three Interconnected Research Areas
Secure & Privacy-Preserving Distributed Intelligence
Building machine learning and data-sharing systems that remain accurate and useful even when data, participants, or infrastructure cannot be fully trusted.
Learn moreAI Security, Cyber Defense & Forensics
Understanding how intelligent systems are attacked, defended, and investigated — from adversarial machine learning to digital forensics of AI-driven incidents.
Learn moreTrustworthy Autonomous & Agentic AI
Ensuring AI agents that retrieve knowledge, invoke tools, and act autonomously remain explainable, accountable, and aligned with human intent.
Learn more