The overarching theme of our research is to improve the security and privacy of online users. We currently have three main research thrusts in the lab that contribute to this theme (but we're open to collaborating on topics outside of these).
We conduct large-scale measurements on the web to understand and characterize harmful online phenomena. Currently, we work on tracking, misinformation, and scams. We are especially interested in measuring harms in less-studied regions.
We develop automated means to detect and prevent security/privacy issues. Of particular interest to us right now are AI-based countermeasures that can run on a user's device rather than on the cloud.
We want to ensure that AI-based countermeasures themselves are not vulnerable. Hence, we investigate attacks that can be conducted on such systems, and design defenses against these attacks.