Youngjoon Yu
Ph. D. Candidate
Image and Video Systems Laboratory
Korea Advanced Institute of Science and Technology (KAIST)
School of Electrical Engineering
email: greatday [at] kaist.ac.kr
Research Interests:
Robust AI, Physical Adversarial Attack/Defense, Causal AI
Education
KAIST, Daejeon, Korea (2020-Present)
Ph.D. in Electrical Engineering
Advisor: Prof. Yong Man Ro
KAIST, Seoul, Korea (2014-2017)
M.S. in Management Engineering
KAIST, Daejeon, Korea (2014)
B.S. in Electrical Engineering
Publications
Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors using Transparent Low-e films
Taeheon Kim, Youngjoon Yu, Yong Man Ro
AAAI Conference on Artificial Intelligence (AAAI), 2023
Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame
Youngjoon Yu*, Hong Joo Lee*, Hakmin Lee and Yong Man Ro (* equal contribution)
IEEE Transactions on Image Processing (TIP), 2022 (Accepted, IF:11.041 )
Defending Physical Adversarial Attack on Object Detection via Adversarial Patch-Feature Energy
Taeheon Kim, Youngjoon Yu, Yong Man Ro
ACM Multimedia (ACM MM), 2022
Robust Decision-based Black-box Adversarial Attack via Coarse-to-fine Random Search
Byeong Cheon Kim*, Youngjoon Yu*, and Yong Man Ro (* equal contribution)
IEEE International Conference on Image Processing (ICIP), 2021
Towards Robust Training of Multi-sensor Data Fusion Network Against Adversarial Examples in Semantic Segmentation
Youngjoon Yu, Hong Joo Lee, Byeong Cheon Kim, Jung Uk Kim, and Yong Man Ro
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 [paper]
Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning
Youngjoon Yu, Hong Joo Lee, Byeong Cheon Kim, Jung Uk Kim, and Yong Man Ro
arXiv preprint arXiv:2005.10987, 2020 [paper]
Professional Activities
Reviewer of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Reviewer of Computer Vision and Pattern Recognition (CVPR)
Reviewer of European Conference on Computer Vision (ECCV)
Reviewer of IEEE International Conference of Acoustics, Speech, and Signal Processing (ICASSP)
Awards & Honors
The Best Presentation Award
KAIST-Korea Agency for Defence Development Workshop, 2022
The Best Paper Award
Military Operations Research Society of Korea, 2020
News Articles
- 딥러닝, 적대적 공격 막는 방어 프레임 개발...KAIST, 인공지능 방어 성능 강화!, AI Times, 2022.11.15