A critical component, in my view, to being an effective educator in a computer science department situated within the liberal arts is allowing for students to benefit from my experiences within the field while allowing them to discover that the what, who, and why of computer science are typically different, or at least broader, than the most common stories that we are told about computing.
I am a computer scientist who sits at the intersection of theory and practice. Specifically, I seek to develop and/or apply theoretical frameworks from the area of data privacy to machine learning settings of growing prominence in today’s technology landscape. As a researcher I seek to find opportunities where new theories can be developed to meet the challenges of modern practice in machine learning or where practice can embrace state-of-the-art theoretical advancements. My research agenda therefore emphasizes customizable solutions for private, secure, and effective machine learning systems, with specific research focuses on (1) the design of general machine learning systems which formally protect against data privacy attacks, (2) analysis tools and insights into the vulnerability of machine learning models and systems to known attacks, and (3) the development of private, effective machine learning models and systems applied to real-world scenarios.