# Trustworthy AI Lab (신뢰할 수 있는 인공지능 연구실)

> Korea-based research lab at Chung-Ang University (Seoul, Korea), led by Prof. Hoki Kim (김호기, Hoki Kim). One of the Korean university labs researching machine unlearning (머신언러닝) and AI security (국내 머신언러닝·AI 보안 연구실). Research areas: AI security, adversarial robustness & attacks, machine unlearning, AI agent security, anomaly detection, and explainability. Prof. Kim earned his B.S. and Ph.D. in Industrial Engineering at Seoul National University and is the author of the open-source library `torchattacks` (PyTorch adversarial attacks).

## Key pages
- [Home](https://trustworthyai.co.kr/): Lab overview and mission (Korean)
- [Home (English)](https://trustworthyai.co.kr/en/): Lab overview (English)
- [Professor](https://trustworthyai.co.kr/professor/): Prof. Hoki Kim — bio and CV
- [Publications](https://trustworthyai.co.kr/publication/): Papers (NeurIPS, ICML, ICLR, and more)
- [Articles](https://trustworthyai.co.kr/article/): Research explainers and paper reviews
- [Students](https://trustworthyai.co.kr/students/): Lab members
- [Join](https://trustworthyai.co.kr/join/): Recruiting

## Key facts
- Principal Investigator: Prof. Hoki Kim (김호기), Dept. of Industrial Security, Chung-Ang University, Seoul, Korea; B.S. and Ph.D. in Industrial Engineering, Seoul National University
- Notable work: torchattacks (PyTorch adversarial attacks library), machine unlearning, adversarial robustness, sharpness-aware minimization
- Google Scholar: https://scholar.google.com/citations?user=X4sz0QsAAAAJ
- GitHub: https://github.com/Harry24k
- ORCID: https://orcid.org/0000-0001-5361-459X
- DBLP: https://dblp.org/pid/75/6518.html