My research focuses on Trustworthy Artificial Intelligence, AI Control, Artificial Conscience, AI-Human Socialization, Trust Engineering, System Security and Networking. I am particularly interested in measuring, managing, and using trust among various interacting actors, such as humans-humans, humans-machines, and machines-machines, to develop better decision-making systems in critical fields, including security, healthcare, networks, finance, managing physical and computing resources, and so on. We use our newly developed trust management framework based on measurement theory, already validated that is simple and flexible to be applied to various applications. Essential goals for our trust-based decision-making systems include trustworthiness, reliability, security, robustness, explainability, scalability, economic viability, and manageability.

Curriculum Vitae

New class announcements

News and Accomplishments

eXTReMe Tracker