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.

Recent News

  • Jan 2026 Jailbreak Poisioning paper submitted to ICML (Pre-print soon)!
  • May 2025 Joined Berkeley NLP Group!
  • Mar 2025 Completed 18 Months of Korean Military Service!

* = equal contribution

ICLR 2024 · Conference Paper

Defending Against Transfer Attacks From Public Models

Chawin Sitawarin, Jaewon Chang*, David Huang*, Wesson Altoyan, David Wagner

In the Twelfth International Conference on Learning Representations (ICLR), 2024

PDF Code Project
@inproceedings{sitawarin_defending_2024, title = {Defending against Transfer Attacks from Public Models}, booktitle = {The Twelfth International Conference on Learning Representations}, author = {Sitawarin, Chawin and Chang{${*}$}, Jaewon and Huang{${*}$}, David and Altoyan, Wesson and Wagner, David}, year = {2024}, month = jan, url = {https://openreview.net/forum?id=Tvwf4Vsi5F}, archiveprefix = {arxiv}, }
Paper teaser

Projects

Teaching

  • CS 170, Efficient Algorithms - Fall 2025, Spring 2026
  • EECS 16A, Circuits & Linear Algebra - Fall 2022, Spring 2023
  • CS 70, Discrete Math & Probability - Spring 2023 (Academic Intern)
  • CS 61C, Computer Architecture - Spring 2023 (Academic Intern)

Coursework

  • Fall 2021 CS 61A, EECS 16A, Math 53
  • Spring 2022 CS 61B, CS 70, EECS 16B
  • Fall 2022 CS 61C, CS 170, Math 110
  • Spring 2023 CS 189, EECS 126, EECS 127
  • Fall 2025 Physics 7A, CS 162, CS 182, EECS 183
  • Spring 2026 Physics 7B, CS 184, EE290-16

Notes

I enjoy teaching; happy to chat about coursework, research, or project ideas.