MYUNG-JOON KWON (권명준)

Education

• 2021.2 - Present        Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea

• 2019.2 - 2021.2          M.S. (School of Computing),  Korea Advanced Institute of Science Technology, South Korea

• 2015.2 - 2019.2          B.S. (Mathematics and Computer Science), Sogang University, South Korea

Research Interests

• Computer Vision 

• Machine Learning

• Multimedia Forensics

Projects

• [2023.2 - Present] A Study on CAPTCHA Solving Techniques to Discover its Vulnerabilities (캡차 취약요소 발굴을 위한 우회기법 연구), 카이스트 안보기술연구센터 

• [2021.4 - 2022.12] Development of photorealistic digital human creation and 30fps realistic rendering technology (실사 수준의 디지털 휴먼 생성과 30fps급 실감 렌더링 기술 개발), Institute for Information and Communications Technology Promotion (정보통신기획평가원)

• [2022.2 - 2022.12] 알고리즘을 통한 AI 안면인식 교란 대응 고도화, 카이스트 안보기술연구센터 

• [2021.1 - 2021.11] AI 안면인식 교란 기술 고도화, 카이스트 안보기술연구센터 

• [2020.3 – 2020.11] Study on fundamental technology for Deepfake video detection through Corner-case research (코너 케이스 연구를 통한 딥페이크 동영상 탐지 기반 기술 연구), 카이스트 안보기술연구센터 

• [2019.2 – 2020.22] Development of high reliability image and video authentication service for smart media environment (스마트미디어 환경을 위한 고신뢰 영상 및 동영상 무결성 인증 서비스 개발), Institute for Information and Communications Technology Promotion (정보통신기획평가원)

Honors & Awards

• 대한전자공학회 2022 하계학술대회 우수학생논문상 (권명준, 손민지, 김윤지, 김창익, "적대적 취약성 다양화를 통한 적대적 전이성 향상")

• 대한전자공학회 2022 하계학술대회 우수논문상 (전우진, 김윤지, 권명준, 김창익, "스테레오 깊이 추정 신경망에 대한 표적성 적대적 공격")

• 대한전자공학회 2022 하계학술대회 산업체(LG) 관심논문상 (손민지, 권명준, 김희선, 김창익, "생성 모델 기반 적대적 공격의 전이성 향상을 위한 구분 모델의 특성 지도 마스킹 방법")

Publications

• Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, and Changick Kim, "Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models", Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

• Junyoung Byun, Myung-Joon Kwon, Seungju Cho, Yoonji Kim, Changick Kim, "Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24648-24657, 2023.

• Minji Son, Myung-Joon Kwon, Hee-Seon Kim, Junyoung Byun, Seungju Cho, and Changick Kim, "Adaptive Warping Network for Transferable Adversarial Attacks", IEEE International Conference on Image Processing (ICIP), 2022

• Seungju Cho, Junyoung Byun, Myung-Joon Kwon, Yoonji Kim, and Changick Kim, "Adversarial Training with Channel Attention Regularization", IEEE International Conference on Image Processing (ICIP), 2022

• Myung-Joon Kwon, SH Nam, IJ Yu, H Lee, and Changick Kim, "Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization", International Journal of Computer Vision (IJCV), vol 130, pp 1875-1895, 2022.

• SH Nam, W Ahn, Myung-Joon Kwon, J Kang, IJ Yu, "DHNet: Double MPEG-4 Compression Detection via Multiple DCT Histograms", IEEE MultiMedia, 2022.

• Junyoung Byun, Seungju Cho, Myung-Joon Kwon, Hee-Seon Kim, and Changick Kim, "Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 15244-15253, 2022.

• Myung-Joon Kwon, IJ Yu, SH Nam, and HK Lee, "CAT-Net: Compression Artifact Tracing Network for Image Splicing Detection and Localization", Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp 375-384, 2021. 

• W Bae, SH Nam, IJ Yu, Myung-Joon Kwon, M Yoon, and HK Lee, "Dual-path convolutional neural network for classifying fine-grained manipulations in H.264 videos", Multimedia Tools and Applications, vol 80, pp 30879–30906, 2021.

• IJ Yu, SH Nam, W Ahn, Myung-Joon Kwon, and HK Lee, "Manipulation Classification for JPEG Images Using Multi-Domain Features", IEEE Access, vol 8, pp 210837–210854, 2020.

• SH Nam, W Ahn, IJ Yu, Myung-Joon Kwon, M Son, and HK Lee, "Deep Convolutional Neural Network for Identifying Seam-Carving Forgery", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol 31, pp3308-3326, 2020.