| Aug 03, 2026 | Excited to be joining INSAIT to start my PhD on LLM security, advised by Dr. Yuxia Wang!  |
| May 01, 2026 | Sockpuppetting, my work on jailbreaking LLMs via prefilling and optimization, was accepted at ICML’s Second Workshop on Agents in the Wild: Safety, Security, and Beyond. Thank you to anyone who stopped by my poster! [paper] |
| Dec 07, 2025 | I had a great time at EurIPS this past week, where I presented my reproducibility study on competitions of mechanisms in LLMs! [paper] |
| Oct 14, 2025 | CLaRE, our work on generated-face detection, was accepted at the 1st ACM Workshop on Deepfake, Deception, and Disinformation Security. [paper] |
| Jun 30, 2025 | Our reproducibility study on the competition of mechanisms in LLMs was accepted at TMLR and MLRC! [paper] |