Defending Against Transfer Attacks From Public Models
In the Twelfth International Conference on Learning Representations (ICLR), 2024
Hello, I'm Jaewon, an undergraduate at UC Berkeley studying EECS. I'm currently involved in research at Berkeley AI Research, working with both the Berkeley NLP Group and Professor David Wagner's Security Group. In the NLP group, advised by Alane Suhr, my work focuses on improving task decomposition and reasoning in language models; in the Security Group, advised by Chawin Sitawarin, I study jailbreak poisoning attacks and adversarial learning. Previously, I conducted distributed systems research at Berkeley's Sky Computing Lab under the guidance of Jaewan Hong.
* = equal contribution
In the Twelfth International Conference on Learning Representations (ICLR), 2024
I enjoy teaching; happy to chat about coursework, research, or project ideas.