Our research lab focuses on AI security, data security, and genomic privacy, aiming to develop secure and privacy-preserving machine learning techniques. We are particularly interested in protecting sensitive personal data such as medical records, financial data, and genomic information in AI systems.

Since training AI models requires large-scale data collection, which often includes personal and sensitive data, there is a significant risk of data leakage and privacy violations. To address these concerns, our lab explores and develops:

• Anonymization and encryption techniques for secure data handling

• Federated learning and differential privacy for decentralized and private model training

• Secure synthetic data generation methods for privacy-preserving AI applications

Our ultimate goal is to build trustworthy and secure artificial intelligence systems that uphold data privacy and security in real-world applications.