Chawin Sitawarin

Hello! My name is Chawin Sitawarin (ชวิน สีตวาริน). I am a postdoctoral researcher in the Privacy-Preserving Machine Learning team at Meta.

I am broadly interested in security and privacy aspects of machine learning with a recent focus on large language models. Most of my past works are in the domain of adversarial machine learning, particularly adversarial examples and robustness of machine learning algorithms.

I obtained my PhD degree in Computer Science from UC Berkeley where I was a part of the security group, Berkeley Artificial Intelligence Research (BAIR) and Berkeley DeepDrive (BDD). My advisor was Prof. David Wagner. I have also spent some time at IBM Research, Nokia Bell Labs, and Google Research.

I maintain a list of publications on security and privacy of large language models at llm-sp.
I used to keep track of papers on adversarial examples, but I stopped after the number of papers has become overwhelming. You can still find the list here (last update: Sep 2019).