Xiaoqian Jiang

My laboratory develops privacy-preserving analytics and trustworthy artificial intelligence to advance precision medicine while safeguarding patient confidentiality. Our work integrates cryptography—such as homomorphic encryption and secure multi-party computation—with federated learning, differential privacy, and large-scale machine learning to analyze multimodal biomedical data, including electronic health records, genomic sequences, medical imaging, and wearable-device streams from institutions worldwide. A complementary research focus addresses algorithmic fairness and bias mitigation, ensuring that AI-driven tools deliver equitable benefits across diverse populations. We apply these methods to pressing biomedical challenges, including Alzheimer’s disease subtyping, combinatorial drug repurposing, cancer outcome prediction, and equitable organ-transplant allocation. Our Secure Artificial Intelligence for Healthcare (SAFE) Center hosts a HIPAA-compliant GPU cluster with confidential-computing nodes, providing students and collaborators a unique environment to design, deploy, and evaluate “secure-by-design” AI pipelines.