Decision-making systems based on AI are being used throughout a wide range of real-world scenarios, including healthcare, law enforcement, education, and finance. It is no longer far fetched to envision a future where autonomous systems will be driving critical business and societal decisions. Issues of fairness, privacy, security, and robustness are pervasive when decisions are made using machines. At Columbia Engineering, our goal is to make AI systems more safe, transparent, and accountable through new research in privacy, security, and ethics. Some specific areas of research include AI software security and verification, privacy-preserving algorithm and system design, understanding causality and fairness in AI based decisions, and interpretable models. Application areas include, but are not limited to, computer vision, robotics, autonomous cars, business analytics and automated decision making.
