중앙대학교
신뢰할 수 있는 인공지능 연구실
Hoki Kim
South Korea
본 연구실은 신뢰할 수 있는 인공지능 (Trustworthy AI)을 목표로
세 가지 핵심 개념을 추구합니다.
Our laboratory pursues three core concepts
with the goal of Trustworthy Artificial Intelligence.
안전성은 훈련되지 않은 데이터나 악의적인 조작에 대해서도 안전하게 작동하는 능력입니다. 환경 변화 및 적대적 공격에 대해 강건성을 보장합니다.
Safety is the ability to operate safely even with untrained data or malicious manipulation. It ensures robustness against environmental changes and adversarial attacks.
프라이버시는 인공지능이 데이터의 기밀성을 유지하고 불필요한 개인 정보 수집을 방지하는 능력입니다. 민감 정보 유출 최소화를 보장합니다.
Privacy is the ability of AI to maintain data confidentiality and prevent unnecessary collection of personal information. It ensures minimal leakage of sensitive info.
설명성은 작동 과정과 그 결과를 인간이 이해할 수 있는 형태로 명확히 제시하는 능력입니다. 법적·윤리적 책임을 준수하기 위한 선행 목표입니다.
Explainability is the ability to clearly present the operation process and results in a form that humans can understand. It is a prerequisite for legal/ethical responsibility.
Professor at Industrial Security, Chung-Ang University
B.S. and Ph.D. degrees at Seoul National University
Email hokikim@cau.ac.kr
Professor at Chung-Ang University, focusing on Robustness, Privacy, and Explainability of AI.
Research Interests. As artificial intelligence (AI) continues to drive innovation across a wide range of industries, Trustworthy AI plays a pivotal role in mitigating potential risks and ensuring the safety of AI systems. As a researcher in machine learning and deep learning, I am currently focused on developing Trustworthy AI with the following topics:
Research Experience.
인공지능 신뢰성을 목표로
다양한 파트너와 적극 협력하고 있습니다.
We are working with various partners
to realize Trustworthy Artificial Intelligence.
개인정보보호 AI 기술 협력
[네이버클라우드 & 대검찰청]
Privacy Protection AI Partnership
[Naver Cloud & Prosecution]
기술특례상장 위원
[나이스 평가정보]
Technical Listing Committee
[NICE]
온디바이스 AI 보안 기술 협력
[KIAT & 탑전자산업]
On-device AI Security Partnership
[KIAT & TAP Electronics]
디지털 포렌식 AI 기술 협력
[유락]
Digital Forensic AI Partnership
[UROCK]
규제 준수형 언러닝 기술 개발
[과학기술정보통신부]
Regulatory-Compliant Unlearning
[MSIT]
골프 스윙 분석 AI 기술 협력
[김캐디 & 동국대]
Golf Swing Analysis AI Partnership
[KimCaddie & Dongguk]
본 연구실은 새로운 시각을 제시하며, 영향력 있는 연구에 도전합니다.
최근 5년간 AI 최우수 학회(NeurIPS, ICML, AAAI) 및 SCI 저널에 20편 이상을 게재하였습니다.
Our laboratory challenges impactful research by presenting new perspectives.
We have published 20+ papers in top AI conferences and SCI journals over the past 5 years.
🎉 윤채원 연구원이 애자일소다에서 근무하게 되었습니다.
🎉 Research intern Chaewon Yoon has started working at AgileSoDA.
🎉 이지용 연구원이 토스인컴에서 근무하게 되었습니다.
🎉 Research intern Jiyong Lee has started working at Toss Incom.
🎉 연구실 논문 “Co-occurring Associated REtained concepts in Diffusion Unlearning“이 ICLR 2026에 채택되었습니다.
🎉 Our paper “Co-occurring Associated REtained concepts in Diffusion Unlearning“ is accepted to ICLR 2026.
NeurIPS 2025에서 포스터 발표를 위해 미국 샌디에고 방문 예정입니다.
Attending NeurIPS 2025 for poster presentation in San Diego, USA.
🎉 최대승, 김재성, 김민철 연구원이 “한국전자거래학회 2025 추계학술대회”에서 우수 논문상을 수상하였습니다.
🎉 Research interns Daeseung Choi, Jaeseong Kim, and Mincheol Kim received the Outstanding Paper Award at the 2025 Fall Conference of the Korea Electronic Commerce Association.
🎉 김수민, 장희원, 전소현 연구원이 “중앙대학교 AI·SW융합 우수성과 발표대회”에서 최우수상을 수상하였습니다.
🎉 Research interns Sumin Kim, Heewon Jang, and Sohyun Jeon received the Grand Prize at the Chung-Ang University AI·SW Convergence Excellence Presentation Competition.
🎉 연구실 논문 “Unlearning Aware Minimization“이 NeurIPS 2025에 채택되었습니다.
🎉 Our paper “Unlearning Aware Minimization“ is accepted to NeurIPS 2025.
김재성, 김민철, 최대승 연구원이 “모델추출공격(Model Extraction)” 논문세미나 인턴으로 합류하였습니다.
Undergraduate students Jaesung Kim, Minchethrustworthyai.co.krol Kim, and Daeseung Choi joined as research interns for the “Model Extraction” paper seminar.
김수민, 장희원, 전소현 연구원이 “이상거래탐지(Fraud Detection)” 논문세미나 인턴으로 합류하였습니다.
Undergraduate students Sumin Kim, Heewon Jang, and Sohyun Jeon joined as research interns for the “Fraud Detection” paper seminar.
🎉 연구실 논문 “CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information”이 11th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2025에 게재되었습니다.
🎉 Our paper “CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information” is published in the 11th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2025.
이지용, 윤채원, 박민영 연구원이 “머신언러닝(Machine Unlearning)” 논문세미나 인턴으로 합류하였습니다.
Undergraduate students Jiyong Lee, Chaewon Yoon, and Minyoung Park joined as research interns for the “Machine Unlearning” paper seminar.
NeurIPS 2024에서 포스터 발표를 위해 캐나다 밴쿠버 🇨🇦 방문 예정입니다.
Attending NeurIPS 2024 for poster presentation in Vancouver, Canada 🇨🇦.
🎉 연구실 논문 “Are Self-Attentions Effective for Time Series Forecasting”이 NeurIPS 2024에 채택되었습니다.
🎉 Our paper “Are Self-Attentions Effective for Time Series Forecasting” is accepted to NeurIPS 2024.
🎉 연구실 논문 “Evaluating practical adversarial robustness of fault diagnosis systems via spectrogram-aware ensemble method”가 Engineering Applications of Artificial Intelligence에 게재되었습니다.
🎉 Our paper “Evaluating practical adversarial robustness of fault diagnosis systems via spectrogram-aware ensemble method” is published in Engineering Applications of Artificial Intelligence.
🎉 연구실 논문 “Fair sampling in diffusion models through switching mechanism”이 AAAI 2024에 채택되었습니다.
🎉 Our paper “Fair sampling in diffusion models through switching mechanism” is accepted to AAAI 2024.
🎉 연구실 논문 “Bridged adversarial training”가 Neural Networks에 게재되었습니다.
🎉 Our paper “Bridged adversarial training” is published in Neural Networks.
🎉 연구실 논문 “Fast sharpness-aware training for periodic time series classification and forecasting”가 Applied Soft Computing에 게재되었습니다.
🎉 Our paper “Fast sharpness-aware training for periodic time series classification and forecasting” is published in Applied Soft Computing.
🎉 연구실 논문 “Fantastic robustness measures the secrets of robust generalization”이 NeurIPS 2023에 채택되었습니다.
🎉 Our paper “Fantastic robustness measures the secrets of robust generalization” is accepted to NeurIPS 2023.
🎉 연구실 논문 “Differentially Private Sharpness-Aware Training”이 ICML 2023에 채택되었습니다.
🎉 Our paper “Differentially Private Sharpness-Aware Training” is accepted to ICML 2023.
