Changhoon Kim

Ph.D. 

Arizona State University

Tempe, Arizona

Email: kch AT asu DOT edu

Google Scholar / Linkedin / Twitter

Bio

Changhoon Kim completed his Ph.D. in Computer Engineering at Arizona State University under the advisement of Professor Yezhou Yang. His primary research focuses on the creation of secure machine learning systems. He has dedicated his efforts to developing user-attribution methods for generative models, a critical area of research in the age of AI-generated hyper-realistic content for tracing malicious usage, and machine UNlearning for removing private or harmful content from AI models. Kim’s pioneering research has been recognized at prestigious conferences such as ICLR, ICML, ECCV, and CVPR. Additionally, he holds a U.S. patent for user-attribution in generative models. To further contribute to the community, he organizes tutorials and workshops at leading conferences to emphasize the importance of secure generative AI.

About Me

I have completed my Ph.D. in the School of Computing and Augmented Intelligence (SCAI), where I worked with Prof. Yezhou Yang.



Research Keywords

- Computer Vision

- Generative Models

- Attribution of Synthesized Data

- Robust and Reliability for Generative Models 


News

Jul. 14, 2024 As an organizer, our NeurIPS Workshop on Responsibly Building the Next Generation of Multimodal Foundation Models has been accepted.

Jul. 1, 2024 R.A.C.E. is accepted at ECCV.

Jun. 24, 2024 I have successfully defended my thesis.

Apr. 15, 2024 Invited talk at the Samsung AI Center in Toronto : "Strengthening Image Generative AI"

Apr. 12, 2024 Tutorial on "Responsibly Building Generative Models" is accepted at ECCV 2024

Mar. 29, 2024 Selected as a participant in CVPR 2024 Doctoral Consortium

Feb. 26, 2024 Two papers are accepted  to the CVPR 2024 (WOUAF, ECLIPSE)
Feb. 24, 2024 Talk about Reliable Image Gen-AI at the AAAI Doctoral Consortium 2024

Jan. 12, 2024 Interview with AIhub is available at Link 

Jan. 9, 2024 Presented  "Tutorial on Reliability of Generative Models in Vision" WACV 2024 Tutorial

Publications & Patents

Changhoon Kim*, Kyle Min*, Maitreya Patel, Sheng Cheng,  Yezhou Yang

CVPR 2024, Demo

Maitreya Patel , Changhoon Kim, Sheng Cheng, Chitta Baral, Yezhou Yang

CVPR 2024

Guangyu Nie*, Changhoon Kim*, Yezhou Yang, Yi Ren

International Conference on Machine Learning (ICML 2023)

Patent

Changhoon Kim, Yi Ren, Yezhou Yang

US Patent App. 17/544,201

Yongbaek Cho*, Changhoon Kim*, Yezhou Yang, Yi Ren

International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP 2022)

Changhoon Kim*, Yi Ren*, Yezhou Yang

International Conference on Learning Representations (ICLR 2021)

Changhoon Kim, Mengyuan Zhang, Chongjie Zhang, Xi Jessie Yang

Human Factors and Engineering Society (HFES 2018)

Invited Talks

Topic: Strengthening Image Generative AI


Topic: Risk Management in Image Generative Models through Model Fingerprinting


Topic: Enhancing the reliability of image generative AI


Topic: Generative Model's Risk Management in Medical Domain


Topic: Text-to-Image Generative Model's Risk Management with User Attribution


Intelligent Architecture & Systems Research lab. 

Topic: Decentralized Attribution of Generative Models

Honor

Service

Organizer 

Reviewer


Work Experience

KRAFTON, South Korea, 2022 Summer


GEOMania Co., South Korea, 2011-2014

Teaching Experience

CSE 110 - Principles of Programming (2018 Fall, 2019 Spring)

CSE 100 - Principles of Programming (2019 Spring)

Collaborators

I am fortunate to work with these great people:   Kyle Min (Intel Labs.), Maitreya Patel (ASU), Sheng Cheng (ASU)