Hoki Kim
Professor at Industrial Security, Chung-Ang University, South Korea.
B.S. and Ph.D. degrees at Seoul National University, South Korea.
Email hokikimkr@gmail.com
Research Interests. As artificial intelligence (AI) continues to drive innovation across a wide range of industries, Trustworthy AI (Korean-only) 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:
- Adversarial Robustness: adversarial attacks and adversarial defenses [NeurIPS 2023, Top AI Conf.; AAAI 2021, Top AI Conf.; NeuNet, IF Top 10%]
- Generalization: sharpness-aware minimization [ICML 2023, Top AI Conf.], domain adaptation [PR, IF Q1]
- Industrial Applications: prognostics and health management [EAAI, IF Top 5%], audio classification [PR, IF Q1], time series forecasting [ASOC, IF Q1]
Research Experience.
- Projects with Samsung Electronics, Incheon Airport, and the Ministry of Science and ICT (MSIT), etc.
- Reviewer in NeurIPS, ICML, IEEE Transactions on Image Processing, and IEEE Transactions on Information Forensics & Security, etc.
- Developer of torchattacks(★1800+) and torchbnn(★450+).