TrustBrew Lab ☕️
We focus on building trustworthy and socially responsible AI systems.
Our research spans robustness, privacy, and interpretability of AI models, with a particular emphasis on the evolving landscape introduced by large foundation models such as LLMs and multi-modal LLMs.
In addition to core technical challenges, we actively explore interdisciplinary applications of trustworthy AI in domains like cybersecurity, education, and healthcare.
People
Principal Investigator
- Dr. Xi Li, Assistant Professor, CS@UAB
PhD Students
- Peiyuan Zhang – Fall 2025 – Present
- Shirong Kou – Fall 2025 – Present
Mentored Students
- Xiaohuan Bi – Undergraduate at Renmin University of China
- Falong Fan – M.S. from The Chinese University of Hong Kong, Shenzhen
- Ruofan Mao – Master's student at UAB
Join Us 🙌
I’m looking for highly motivated PhD students to join my research group starting in Fall 2025 at CS@UAB.
Please check the Recruitment page for more details.
If you are interested, apply to the
CS PhD program
and mention my name in your application.
Additionally, send your CV and transcript to
xili.recruitment@gmail.com
with the subject [25Fall PhD Application].
Research Projects
Evolving Safety Landscape of Large Foundation Models
- Tutorial: Towards Safe Multi-Modal Learning: Unique Challenges and Future Directions – ICCV 2025.
- Tutorial: Exploitation and Mitigation: Understanding Large-Scale Machine Learning Robustness under Paradigm Shift – SDM 2025.
Robustness of LLMs and Multi-Agent Systems
- Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models – ACL(findings) 2025.
- PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning – IEEE IRI 2025.
A PhD Is a Marathon
🌱 You Are More Than Your PhD
- Your PhD is not your whole identity. You are more than your research.
- Enjoy your life. Value your family, friends, and fluffy pets.
- Don’t let papers or citations label you. They’re easy to measure, but they can’t define your worth or potential.