I am a PhD student at Princeton University, advised by Prof. Prateek Mittal. I primarily work on AI security.
I developed a series of certifiably robust defenses against adversarial patch attacks, including PatchGuard, PatchGuard++, PatchCleanser, PatchCURE, DetectorGuard, and ObjectSeeker. Here is a short survey on this topic.
Recently, I have been working on LLM security, e.g., RobustRAG.
I graduated from Shanghai Jiao Tong University (SJTU) with a Bachelor's degree in 2019. I was a member of Network Security and Privacy Protection (NSEC) Lab and was advised by Prof. Haojin Zhu (2016-2019). I also worked with Prof. Bo Li as a research intern at University of Illinois Urbana-Champaign (2018).
Here is my [Curriculum Vitae]. Please feel free to reach out via email at cxiang@princeton.edu :)