경력 및 학력
Career & Education
조교수(Assistant Professor)
Assistant Professor
중앙대학교 산업보안학과(Industrial Security, Chung-Ang University)
Department of Industrial Security, Chung-Ang University
2024 - 現
2024 - Present
연수연구원(Postdoctoral Researcher)
Postdoctoral Researcher
서울대학교 공학연구원(Institute of Engineering Research, Seoul National University)
Institute of Engineering Research, Seoul National University
2024
2024
박사과정(Ph.D.)
Ph.D.
서울대학교 산업공학과(Industrial Engineering, Seoul National University)
Department of Industrial Engineering, Seoul National University
2023
2023
학사과정(B.S.)
B.S.
서울대학교 산업공학과(Industrial Engineering, Seoul National University)
Department of Industrial Engineering, Seoul National University
2018
2018
주요 활동
Professional Activities
주식회사 유락 AI 보안 기술 자문 위원
Committee Member for AI Security, UROCK
Committee Member for AI Security, UROCK
Committee Member for AI Security, UROCK
2025 – 現
2025 – Present
NICE 평가정보 기술특례상장 평가 자문위원
Advisory Committee Member for Technology-Based IPO Screening, NICE
Advisory Committee Member for Technology-Based IPO Screening, NICE
Advisory Committee Member for Technology-Based IPO Screening, NICE
2024 – 現
2024 – Present
최우수 AI 학회(NeurIPS, ICML, ICLR, AAAI) 리뷰어 및 프로그램 위원회 위원
Reviewer and Program Committee Member for Top-Tier AI Conferences (NeurIPS, ICML, ICLR, AAAI)
Reviewer and Program Committee Member for Top-Tier AI Conferences (NeurIPS, ICML, ICLR, AAAI)
Reviewer and Program Committee Member for Top-Tier AI Conferences (NeurIPS, ICML, ICLR, AAAI)
2023 – 現
2023 – Present
한국신용정보원 금융권 AI 플랫폼 전문가
AI Platform Specialist for the Financial Sector, KCIS
AI Platform Specialist for the Financial Sector, KCIS
AI Platform Specialist for the Financial Sector, KCIS
2025
2025
중앙대 안전한 데이터 활용 전문가 과정 참여교수
Participating Faculty, Secure Data Utilization Expert Program, Chung-Ang University
Participating Faculty, Secure Data Utilization Expert Program, Chung-Ang University
Participating Faculty, Secure Data Utilization Expert Program, Chung-Ang University
2024
2024
대표 논문
Selected Publications
최우수 AI 논문 7편 + SCI 논문 15편, 총 26편 이상 논문 게재
Top-tier AI papers 7 + SCI journal papers 15, total 26+ publications
- Chaewon Yoon, Jiyoung Lee, and Hoki Kim. "Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management." IEEE Transactions on Industrial Informatics, 2026 (SCIE Top 5%)
- Dongbin Kim, Jaewook Lee, and Hoki Kim. "Pattern-guided forecasting framework for metal price prediction with grouping decomposed series." Financial Innovation, 2026 (SSCI Top 1%)
- Hoki Kim, Keonwoo Kim, Sungwon Chae, and Sangwon Yoon. "Unlearning-Aware Minimization." In Thirty-ninth Conference on Neural Information Processing Systems, 2025 (NeurIPS)
- Hoki Kim, Jinseong Park, Yujin Choi, and Jaewook Lee. "Fantastic Robustness Measures: The Secrets of Robust Generalization." In Thirty-seventh Conference on Neural Information Processing Systems, 2023 (NeurIPS)
- Hoki Kim, Woojin Lee, and Jaewook Lee. "Understanding Catastrophic Overfitting in Single-step Adversarial Training." In Proceedings of the AAAI Conference on Artificial Intelligence, 2021 (AAAI)
주요 과제 및
프로젝트 Major Grants & Projects
프로젝트 Major Grants & Projects
프라이버시 규제 준수를 위한 적대적 공격에 견고한 머신러닝 기술 개발 (9,200 만원, 연구책임자)
Robust Machine Learning Against Adversarial Attacks for Privacy Regulation Compliance (KRW 92M, PI)
적대적 공격에 대한 데이터 유출을 방지하는 견고한 머신언러닝 기술 개발
Robust machine unlearning to prevent data leakage against adversarial attacks
2025.09 – 現
2025.09 – Present
결함감지 온디바이스(On-Device) AI 의 보안 솔루션 개발 (14,300 만원, 연구책임자)
Security Solution for Defect-Detection On-Device AI (KRW 143M, PI)
온디바이스(On-Device) AI 모델의 해킹 및 리버스 엔지니어링을 방지하기 위한 경량화 친화적 입력 변형 기반 보안 기법 및 구조 난독화 기술 개발
Lightweight input-transformation security methods and architecture obfuscation to prevent hacking and reverse engineering of on-device AI models
2025.04 – 現
2025.04 – Present
데이터 안전 활용을 위한 차세대 보안 핵심기술 개발 (750,000 만원, 연구참여자)
Next-Generation Core Security Technologies for Safe Data Utilization (KRW 7.5B, Research Participant)
AI 기반 민감정보 보호를 위한 융합형 인재 양성과 국제 수준의 데이터보안 연구환경 구축
Training convergent talent and building a world-class data-security research environment for AI-based sensitive information protection
2024.07 – 現
2024.07 – Present
융합보안대학원 (550,000 만원, 연구참여자)
Graduate School of Convergence Security (KRW 5.5B, Research Participant)
디지털 금융 보안 생태계 조성을 위한 실무 중심의 전문 보안 인재 양성과정 운영
Practice-oriented advanced security training program for building a digital finance security ecosystem
2023.07 – 現
2023.07 – Present
기타 사항
Other Information
오픈소스 및 특허
Open Source & Patents
- torchattacks: PyTorch 기반 적대적 공격 라이브러리 (Github Star ☆ 2,000+, 다운로드 290,000+, 인용 300+) torchattacks: PyTorch-based adversarial attack library (GitHub Star ☆ 2,000+, 290,000+ downloads, 300+ citations)
- torchbnn: PyTorch 기반 베이지안 신경망 라이브러리 (Github Star ☆ 500+, 다운로드 110,000+, 인용 90+) torchbnn: PyTorch-based Bayesian neural network library (GitHub Star ☆ 500+, 110,000+ downloads, 90+ citations)
- 인공지능 신뢰성 관련 특허 등록 2 건 및 출원 7 건 (적대적 음성 예제 감지 시스템 등) 2 registered and 7 filed patents on AI trustworthiness (e.g., adversarial speech example detection system)
강의 교과목
Courses Taught
- 안전한 인공지능 (Safe Artificial Intelligence) Safe Artificial Intelligence
- 인공지능 규제와 신뢰성 (AI Regulations and Trustworthy) AI Regulations and Trustworthiness
- 융합보안학 (Convergence Security Science) Convergence Security Science