Fuqiang Liu | AI Safety

My research focuses on AI safety, specifically, to identify the potential risks hidden in powerful AI systems and develop resilient solutions for practical intelligent applications. Completed research projects are:

1. Potential Risks in LLMs for Time Series Forecasting

• Adversarial attacks against LLM in time series forecasting. link
  [AISTATS’25]
• Temporally sparse attacks against LLM in time series forecasting. link
  [ICLR’25 BuildingTrust]

2. Resilient Intelligent Transportion System (ITS)

• Accumulated and autocorrelated error adjustment for more accurate ITS. link
  [TITS’22] [INFFUS’25]
• Adversarial danger identification for more robust ITS. link
  [TNNLS’23]

Background

I graduated with my Ph.D. in Intelligient Transporation System (ITS) from McGill University, Canada, co-supervised by Prof. Lijun Sun and Prof. Luis Miranda-Moreno. Prior to my doctorate, I earned two Master of Science (MSc) degrees in Electrical and Computer Engineering from Beijing Institute of Technology (BIT), China, and Clarkson University, USA. I also hold a Bachelor’s degree in Electrical and Electronic Engineering from BIT, China.