Wai Man (Raymond) Si

I am a Ph.D student at CISPA Helmholtz Center for Information Security, supervised by Prof. Michael Backes and advised by Dr. Yang Zhang. Prior to that, I received my B.S. (2018) and M.S. (2021) degrees from Georgia Institute of Technology. where I am fortunate to work with Prof. Alexander Lerch and Prof. Mark Riedl.

My research focuses on attacks targeting NLP models, including adversarial and poisoning attacks. I am also interested in developing safer models through post-training techniques. Currently, my work explores LLM behavior using mechanistic interpretability, as well as lightweight methods for steering or modifying model behavior.