Hanwei ZHANG’s Homepage

Hi! Welcome to my homepage.

I am a postdoctoral researcher at Saarland University under the chair of Prof. Holger Hermanns, where I explore trustworthy artificial intelligence.

My work centers on understanding and improving the reliability of machine learning systems, with a particular emphasis on adversarial attacks and model interpretability. I study how and why modern AI systems fail under adversarial conditions, and develop methods to make their behavior more transparent and robust. My research aims to bridge theoretical insights and practical applications, contributing to the development of AI systems that can be trusted in real-world settings.

I enjoy working across disciplines and collaborating with others to tackle challenging questions. My research experience spans international and interdisciplinary settings, shaping how I approach problem-solving and innovation.

More broadly, I am motivated by curiosity and a desire to better understand and contribute to problems that lie at the intersection of security, reliability, and explainability in AI.