Tel: +82-42-350-7521
E-Mail: hskim98[at]kaist.ac.kr
Education
2023.3 - Present Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
2021.3 - 2023.2 M.S. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea
2017.3 - 2021.2 B.S. (School of Electrical Engineering), Ulsan National Institute of Science and Technology, South Korea
Research Interests
Computer Vision
LVLM Robustness & Jailbreak
Video Analysis
Mamba Architecture
AI Robustness & Adversarial Attack
3D Object Detection & Depth Estimation
Projects
2021.03 ~ 2021.11 물리적 패턴을 통한 AI 안면인식 교란 기술 연구 (Physical adversarial attack)
2021.03 ~ 2021.11 알고리즘을 통한 AI 안면인식 교란 대응기술 고도화 (Digital-domain adversarial attack)
2022.02 ~ 2022.12 Adversarial Attack (3rd year)
2022.05 ~ 2024.12 Precise landing technology for drones
2023.02 ~ 2023.12 Captcha(Completely Automated Public Turing test to tell Computers and Humans Apart) 기술 고도화
2024.01 ~ 2027.12 Video Adversarial Attack 고도화 (Universal adversarial perturbations)
2025.01 ~ 2028.12 회복탄력성 있는 Multimodal Large Language Model (MLLM) 기술 연구
Publications
Seokil Ham, Hee-Seon Kim, Sangmin Woo, and Changick Kim, "Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 11-15, 2025.
Jinyoung Park*, Hee-Seon Kim*, Kangwook Ko*, Minbeom Kim, and Changick Kim, "VideoMamba: Spatio-Temporal Selective State Space Model," in Proc. IEEE/CVF European Conference on Computer Vision (ECCV), Oct. 02 - 06, 2024. (* These three authors contributed equally)
Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, and Changick Kim. “Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, Oct. 02 - 06, 2023.
Inyong Koo*, Inyoung Lee*, Se-Ho Kim, Hee-Seon Kim, Woo-jin Jeon, and Changick Kim. “PG-RCNN: Semantic Surface Point Generation for 3D Object Detection,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, Oct. 02 - 06, 2023. (* These two authors contributed equally)
Minji Son, Myung-Joon Kwon, Hee-Seon Kim, Junyoung Byun, Seungju Cho, and Changick Kim, "ADAPTIVE WARPING NETWORK FOR TRANSFERABLE ADVERSARIAL ATTACKS", in Proc. the 29th IEEE International Conference on Image Processing (ICIP), Bordeaux, France, Oct. 16-19, 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," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 19-24, 2022.
김희선, 권명준, 변준영, 김창익, "카메라 시점 변환을 이용한 전이 기반 적대적 공격 기법," 대한전자공학회논문지, Jul. 2022.
김희선, 변준영, 손민지, 김창익, "혼합 이미지를 통한 보편적 적대적 섭동의 공격 성공률 향상", 대한전자공학회 하계학술대회, 제주신화월드 랜딩컨벤션센터 제주, Jun. 29- Jul. 1, 2022.
김희선, 권명준, 변준영, 김창익, "원근 변환 기법을 통한 적대적 이미지의 전이성 향상," 대한전자공학회 추계학술대회, 송도컨벤시아 인천, Nov. 26-27, 2021.
고강욱, 박연주, 김윤지, 김희선, 심규진, 김창익, "거리두기 손실 함수를 통한 자기지도 대조 학습의 성능 향상", 대한전자공학회 하계학술대회, 제주신화월드 랜딩컨벤션센터 제주, Jun. 29- Jul. 1, 2022.
김민범, 김희선, 변준영, 김창익, "이중 무작위 변환 기법을 통한 보편적 적대적 섭동의 전이성 향상", 대한전자공학회 하계학술대회, 제주신화월드 랜딩컨벤션센터 제주, Jun. 29- Jul. 1, 2022.
손민지, 권명준, 김희선, 김창익, "생성 모델 기반 적대적 공격의 전이성 향상을 위한 구분 모델의 특성 지도 마스킹 방법", 대한전자공학회 하계학술대회, 제주신화월드 랜딩컨벤션센터 제주, Jun. 29- Jul. 1, 2022.