Emily Black is a postdoctoral scholar at Stanford University’s RegLab. She recently graduated with her PhD from Carnegie Mellon University, where she was advised by Professor Matt Fredrikson. Emily’s research is in the area of fairness, accountability, and transparency in AI. Her recent work has focused on connecting problems of instability and fairness in deep learning algorithms, developing explanation techniques for machine learning models, and investigating fairness effects of various government uses of AI systems. While at RegLab, she will be working on the fairness impacts of AI systems in tax audit selection.