UVA-DSA

At UVA Dependable Systems & Analytics group, we build the next-generation of Resilient Cyber-Physical Systems. We take a multidisciplinary approach to safety and security assurance of CPS, with applications to medical devices, surgical robots, and autonomous systems. By leveraging techniques from dependable computing and fault-tolerance, machine learning, and real-time systems, we develop integrated model and data-driven methods, realistic testbeds and simulators, and datasets to analyze incidents, assess resilience to faults and attacks, and enable runtime monitoring for detection and mitigation of adverse events.

Resilient Cyber-Physical Systems for Robotic Surgery

This project aims to enhance the safety and efficiency of robot-assisted surgical procedures by combining systematic modeling of safety incidents, resilience assessment under faults and cyber threats, continuous context-aware monitoring, and simulation-based training for surgical teams:

Modeling and analysis of safety incidents by considering the interactions among cyber and physical system components and human operators;
Resilience assessment of the robotic surgical systems in the presence of accidental system faults, cyber attacks, and human errors;
Continuous context-aware monitoring for early detection of potential safety and security violations;
Simulation-based safety training to prepare surgical teams on dealing with unexpected events during surgery.

Cognitive Assistant Systems for Emergency Response

This project focuses on developing the next generation of first responder technologies that enhance situational awareness and safety in emergency response. The central goal is to design a wearable cognitive assistant system that integrates the following key components:

Resilient data analytics for collecting heterogeneous data streams from the incident scene, aggregating them with knowledge bases and publicly available sources, and transforming the results into accurate, actionable feedback for first responders;
Anytime real-time sensing and edge computing resources that are dynamically optimized to enable continuous data processing on responder-worn devices, even under unexpected events such as hardware failures or network disconnections.

Resilience-by-Construction Design of Medical Devices

This project explores the development of generalized, model-based fault-tolerance techniques grounded in the principle of resilience-by-construction to guide the design of next-generation medical devices. Advances in low-power, highly integrated technologies have opened enormous opportunities for deploying implantable medical devices (IMDs) and body area networks (BANs). At the same time, rising device complexity, strict resource constraints, and shrinking time-to-market have introduced critical challenges for ensuring reliability, security, and patient safety. By embedding resilience directly into the design process, this work aims to create medical devices that are robust, dependable, and secure by construction.

Dependable and Secure Artificial Intelligence for Autonomous Vehicles

This project focuses on the design and validation of resilient autonomous systems that depend on artificial intelligence and machine learning for perception, control, and decision-making. As these systems increasingly underpin safety-critical cyber-physical applications such as autonomous vehicles, ensuring their reliability, security, and trustworthiness has become essential. Our work emphasizes the development of safety monitoring and mitigation mechanisms, as well as rigorous testing and certification techniques tailored for machine learning–based components, with the goal of enabling dependable deployment of autonomous CPS.