Trustworthy Artificial Intellgence (TAI) Lab
We are a research lab in Machine Learning Group, School of Computing Science, Simon Fraser University led by Dr. Linyi Li.
Our research aims to advance the general trustworthiness of artificial intelligence, with a focus on deep learning models empowering the state-of-the-art genAI such as language models. Our mission is to deliver AI technologies that are reliably aligned with human values, so as to minimize the negative impacts of powerful AI.
Specifically, we conduct research in:
- Understanding AI in a principled way: We evaluate AI models with scientific benchmarks, advanced localization & attribution techniques, and theoretical frameworks to understand how model works and why existing trustworthiness threats exist.
- Delivering certifiable mitigations: We are the leading team in developing certifiable mitigations for deep learning models so as the AI model comes with practical guarantees of trustworthiness when deployed in the wild world.
Our lab is located in the beautiful Burnaby campus of Simon Fraser University in the greater Vancouver area, Canada.
Interested in research mentorship or collaborations?
- For SFU student: Welcome to check out our course page to learn, or send us an email for potential research opportunities.
- For research mentorship or PhD/Msc program: Welcome to check out here.
- For research collaboration: Welcome to send us an email directly.