이재욱 연구실

AI Safety, Privacy-preserving AI, Stable Machine Learning

Proposed robustness analysis and defense methods against adversarial attacks across diverse domains including time series, speech, and fault diagnosis.

Developed privacy-preserving and fair AI learning methods by leveraging differential privacy, homomorphic encryption, and generative model-based data synthesis.

Developed generalizable and stable learning algorithms including noise reduction and domain-invariant representation learning for industrial applications.

Developed global optimization algorithms based on multi-basin dynamical systems and established theoretical foundations for stability analysis.

Financial AI, Blockchain, Digital Assets including Stablecoins, Cryptocurrencies, NFTs, and CBDC

Application of AI technologies to portfolio optimization and asset pricing by integrating Black-Litterman model with large language models and machine learning.

Empirical studies on blockchain market structures including analysis of digital currencies, MEV detection, and investigations into market events.