Jaewon Chang

Undergraduate Student

University of California, Berkeley

changjaewon0315@berkeley.edu

About me

Hello, I'm Jaewon! I'm an undergraduate student at Berkeley studying EECS and pure mathematics. My research interests gravitate towards adversarial learning in ML and addressing memory underutilization in Systems. After two years at Berkeley, I took a detour and enlisted in the South Korean army. Before that, I've been fortunate to have been involved in research at BAIR and SkyLab, under the guidance of Chawin Sitawarin and Jaewan Hong respectively.

At BAIR, I've been involved in developing robust defenses against adversarial attacks, which have previously been proven to be transferable across neural networks. Meanwhile, at SkyLab, I used to work on developing ways to tackle the challenge of memory underutilization within peer-to-peer networks.

Recently, I've been spending most of my free time in the army reading non-fiction novels like Bad Blood by John Carreyrou, Empire of Pain by Patrick Keefe, among others. I've also been learning about new ML subtopics, including RL and CV.

I also have a great passion for teaching, having mentored numerous middle and high school students in science and math. During my first two years at Berkeley, I've been apart of the EECS 16A course staff for two semesters, and the Academic Intern team for CS 61C and CS 70.

Outside of academics, some of my hobbies include going to the gym, reading novels, and playing league of legends. I was part of Berkeley's division 1 collegiate league of legends team, and my top rank was GM on the korean server!

News

Publications

* = equal contribution

ICLR
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
@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},
keywords = {Computer Science - Artificial Intelligence,Computer Science - Computer Vision and Pattern Recognition,Computer Science - Cryptography and Security,Computer Science - Machine Learning,notion},
}

Projects

Todo-list: A web-accessible todolist

Gomoku: A connect-5 game [CODE]

Teaching

Technical Coursework

Fall 2021

  • [CS 61A] Interpretation of Computer Programs
  • [EECS 16A] Information Devices and Systems I
  • [Math 53] Multivariable Calculus

Fall 2022

  • [CS 61C] Computer Architecture
  • [CS 170] Efficient Algorithms
  • [Math 110] Linear Algebra

Spring 2022

  • [CS 61B] Data Structures
  • [EECS 16B] Information Devices and Systems II
  • [CS 70] Discrete Math and Probability

Spring 2023

  • [EECS 126] Probability and Random Processes
  • [EECS 127] Optimization
  • [CS 189] Introduction to ML