Projects

Research Projects

Causal Fairness for Machine Learning

AI bias is a critical challenge in modern technology. Our team addresses this issue by focusing on causal fairness, emphasizing the importance of causal effects in measuring and mitigating bias in AI systems. Through pioneering research in causal and counterfactual fairness, we ensure AI models produce equitable outcomes by evaluating counterfactual scenarios. In collaboration with the University of Arkansas, we are expanding this research to explore causal fairness in dynamic and non-iid (non-independent and identically distributed) settings, advancing fairness research in complex and evolving environments.

Responsible AI in Healthcare

This project aims to develop responsible and ethical AI models to support lung cancer diagnosis. Collaborating with radiologists from Prisma Health, we focus on creating AI solutions that are fair, equitable, and explainable, ensuring the technology benefits all patient populations without bias. By prioritizing transparency, the project fosters trust and improves patient outcomes. This initiative is generously funded by Prisma Health and the South Carolina EPSCoR program.

Robust Learning for Computer Vision

This project enhances semantic segmentation of off-road terrains by leveraging hyperspectral cameras and advanced causal inference techniques. Specifically, we aim to improve segmentation performance by leveraging hyper-spectural cameras. By coupling hyperspectral data with causal inference methods, we generate accurate representations of off-road environments, ensuring better performance in challenging conditions. This project is supported by United States Army CCDC Ground Vehicle Systems Center.

Responsible and Efficient LLMs

In collaboration with researchers at the University of Maryland, our team is developing responsible and efficient large language models (LLMs). We aim to create LLMs that deliver high efficiency while prioritizing fairness. By addressing challenges such as bias mitigation and resource optimization, we advance LLM technology to ensure it is both ethically sound and computationally efficient, contributing to more sustainable and equitable AI applications.

AI and Cybersecurity Education

Our team is dedicated to developing comprehensive curriculum and hands-on labs in AI and cybersecurity. These unique educational materials provide students with both theoretical knowledge and practical skills, preparing them for real-world challenges in these rapidly evolving fields. To explore the latest labs and resources, visit AI-Cybersecurity Lab.

Acknowledgments

We gratefully acknowledge the generous support from:

• National Science Foundation
• South Carolina EPSCoR Program
• Prisma Health
• United States Army CCDC Ground Vehicle Systems Center
• National Center for Transportation Cybersecurity and Resiliency