중앙대학교
신뢰할 수 있는 인공지능
연구실
Hoki Kim
Chung-Ang University
믿을 수 있는 인공지능을 위한
세 가지 핵심 개념 연구
Researching three core concepts
for trustworthy AI
AI 보안은 악의적 조작 속에서도 AI가 안전하게 작동하도록 지키는 능력입니다. AI를 겨냥한 공격은 물론 LLM·AI 에이전트를 악용한 위협까지 분석하고 방어합니다.
AI security keeps AI operating safely even under malicious manipulation. We analyze and defend against not only attacks targeting AI but also emerging threats that abuse LLMs and AI agents themselves as attack tools.
AI 프라이버시는 AI가 데이터의 기밀성을 지키고 불필요한 개인정보 수집을 막는 능력입니다. 학습 데이터에 담긴 민감정보 유출을 차단해 프라이버시 규제 준수를 돕습니다.
AI privacy is the ability of AI to preserve data confidentiality and avoid unnecessary collection of personal information. It blocks leakage of sensitive information held in training data and supports privacy-regulation compliance.
AI 설명성은 AI의 작동 과정과 의사결정 근거를 사람이 이해할 수 있도록 투명하게 제시하는 능력입니다. 결과에 대한 신뢰와 법적·윤리적 책임을 뒷받침합니다.
AI explainability is the ability to transparently present an AI's process and the rationale behind its decisions in a human-understandable form. It underpins trust in outcomes and legal and ethical accountability.
다양한 파트너와의
신뢰할 수 있는 결과
Trustworthy results
with diverse partners
보안 특화 AI 파운데이션 모델 개발
Cybersecurity-Specialized AI Foundation Model
「AI 보안 위협 대응 매뉴얼」 제작
AI Security Threat Mitigation Manual
기술특례상장 자문위원
AI Evaluation Committee
온디바이스 AI 보안 기술 협력
On-device AI Security Technology
디지털 포렌식 AI 기술 협력
Digital Forensic AI Technology
AI 에이전트 페르소나 신뢰성 연구
AI Agent Persona Trustworthiness
규제 준수형 언러닝 기술 개발
Regulatory-Compliant Unlearning
골프 스윙 분석 AI 기술 협력
Golf Swing Analysis AI Technology
최근 5년 최상위 AI 학회 & SCI 논문
25편 이상 게재
25+ papers in top AI conferences & SCI journals
over the past 5 years
🎉 연구실 논문 “Toward Regulation-Friendly Bearing Fault Diagnosis via Structural Embedding Preserving Machine Unlearning”이 Advanced Engineering Informatics에 게재되었습니다.
🎉 Our paper “Toward Regulation-Friendly Bearing Fault Diagnosis via Structural Embedding Preserving Machine Unlearning” is published in Advanced Engineering Informatics.
🎉 연구실 논문 “Exponential-Tilted Unlearning”이 EMNLP 2026 Findings에 채택되었습니다.
🎉 Our paper “Exponential-Tilted Unlearning” is accepted to EMNLP 2026 Findings.
🎉 김호기 교수가 ICLR 2027의 Area Chair로 선임되었습니다.
🎉 Prof. Hoki Kim has been appointed as an Area Chair for ICLR 2027.
🎉 본 연구실이 참여한 네이버클라우드 컨소시엄이 과학기술정보통신부 「사이버 보안 특화 AI 파운데이션 모델 개발」 사업 수행기관으로 선정되었습니다.
🎉 The NAVER Cloud consortium that our lab participates in was selected as the executing organization for MSIT’s Cybersecurity-Specialized AI Foundation Model Development project.
🎉 정보보호의 날을 맞아, 저희 연구실이 KISA·SK쉴더스와 공동 제작한 「AI 보안 위협 대응 매뉴얼」이 배포되었습니다.
🎉 The AI Security Threat Mitigation Manual, which our lab co-developed with KISA and SK Shieldus, was released for Information Security Day.
🎉 연구실 논문 “Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models”이 ICML 2026에 채택되었습니다.
🎉 Our paper “Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models” is accepted to ICML 2026.
🎉 연구실 논문 “Proactive Defense Benchmark against Deepfake Generation”이 ICML 2026에 채택되었습니다.
🎉 Our paper “Proactive Defense Benchmark against Deepfake Generation” is accepted to ICML 2026.
🎉 연구실 논문 “Stability Analysis of Sharpness-Aware Minimization”이 ICML 2026에 채택되었습니다.
🎉 Our paper “Stability Analysis of Sharpness-Aware Minimization” is accepted to ICML 2026.
🎉 연구실 논문 “Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management”이 IEEE Transactions on Industrial Informatics에 게재되었습니다.
🎉 Our paper “Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management” is published in IEEE Transactions on Industrial Informatics.
🎉 김호기 교수가 중앙대학교 보안대학원 개인정보보호학과 학과장으로 부임하였습니다.
🎉 Prof. Hoki Kim has been appointed as Department Chair of the Department of Privacy Protection, Graduate School of Security, Chung-Ang University.
🎉 이지용 연구원이 토스 인컴에서 근무하게 되었습니다.
🎉 Research intern Jiyoung Lee has started working at Toss Incom.
🎉 연구실 논문 “Pattern-guided forecasting framework for metal price prediction with grouping decomposed series”가 Financial Innovation에 게재되었습니다.
🎉 Our paper “Pattern-guided forecasting framework for metal price prediction with grouping decomposed series” is published in Financial Innovation.
🎉 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 Jaeseong Kim, Mincheol 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 Jiyoung 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.
