Jaehui Hwang

I am a Ph.D student at MCML (Multimedia Computing and Machine Learning) Group under the supervision of Prof. Jong-Seok Lee. I received B.S. degree from Yonsei University in 2019.

I am interested in exploring the properties of various deep learning models to understand neural networks better. In particular, I have focused on analyzing the vulnerability of NNs and what elements including architectural components and input data contribute to the diverse behavior of models. Based on these interests, I aim to contribute to robust and reliable AI systems for diverse tasks and real-world scenarios.

Experiences
• Research intern at Naver AI LAB (Mar. 2022 - Sep. 2022)


Publications


• Conference

Similarity of Neural Architectures using Adversarial Attack Transferability
Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park, Sanghyuk Chun*, Jong-Seok Lee*  
European Conference on Computer Vision (ECCV), 2024 (accepted)   Arxiv

Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability
Jaehui Hwang*, Junghyuk Lee*, Jong-Seok Lee  
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2024   Detail   Arxiv

Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack
Jaehui Hwang, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee
IEEE/CVF International Conference on Computer Vision (ICCV), 2021   Detail   Arxiv

On the Repeatability of EEG-based Image Quality Assessment
Jaehui Hwang, Seong-Eun Moon, Jong-Seok Lee
IEEE International Conference Conference on Systems, Man, and Cybernetics (SMC), 2018   Detail  

TDOA-based ASF Map Generation to Increase Loran Positioning Accuracy in Korea
Jaehui Hwang, Pyo-Woong Son, Jiwon Seo
IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), 2018   Detail  


• Journal

Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks
Jaehui Hwang, Huan Jhang, Jun-Ho Choi, Cho-Jui Hsieh, Jong-Seok Lee
Neural Networks, vol. 169, pp. 388-397, Jan. 2024   Detail   Arxiv

Classifying Gas Data Measured Under Multiple Conditions Using Deep Learning
Hojung Lee, Jaehui Hwang, Hwin Dol Park, Jaehun Choi, Jong-Seok Lee
IEEE Access, vol. 10, pp. 68138-68150, Jun. 2022   Detail  

Universal Kriging for Loran ASF Map Generation
Pyo-Woong Son, Jun Hyo Rhee, Jaehui Hwang, Jiwon Seo
IEEE Transactions on Aerospace and Electronic Systems (TAES), vol. 55, pp. 1828 - 1842, 2018   Detail   -->

Academic activities


• Award

Merit Academic Paper Award
2022-2 Yonsei Superior Paper Awards, Dec 2022


• Reviewer

CVPR 2022-2023, ICCV 2023, TMLR 2023, ECCV 2022


• Talks

Just One Moment: Structural Vulnerability of Deep Action Recognition Against One Frame Attack
Korean Conference on Computer Vision (KCCV), 2022