My background is in studying the effects that machine learning can have on privacy and the ways in which machine learning can be used to attack private systems and infer private information. Currently, my research revolves around the negative impacts of technical optimization systems on the users, non-users, and the environments in which they are deployed. I am particularly interested in developing technologies and methods that measure and counter these negative externalities in situations in which we cannot trust the service provider. For example, countering bias in an unfair system when the service provider is not incentivized to correct it, developing technologies to assist municipalities negatively affected by routing applications or ride-sharing applications, and measuring and countering the effects of fake news and fake accounts on social media platforms. In this context, I am very interested in the effect that the shift to social media platforms for public discourse has on what information we have access to and who has access to it as well as its intersection with censorship.