In her research spanning networking and security, Apostolaki, an assistant professor of electrical and computer engineering, combines machine learning with mathematically grounded techniques to design and build more trustworthy computer networks.

Machine learning can be a powerful tool for managing computer networks. But it sometimes fails in unexpected ways, making it risky to rely on for critical tasks. Apostolaki aims to make machine learning more reliable for networking tasks, like analyzing network traffic for signs of suspicious activity and identifying underlying causes of failures. She will investigate how machine learning is used in networks, identify where and why it can fail, and develop methods to make it more dependable. Her goal is to develop an open-source framework that will help researchers and network operators test and improve machine learning systems used in networking.

Apostolaki joined the Princeton faculty in 2022. She earned her Ph.D. from ETH Zurich in 2021 and completed postdoctoral research at Carnegie Mellon University. She is associated faculty in the Center for Information Technology Policy, DeCenter and the Next-G Initiative, Princeton’s program in advanced communications technology. Her work has won two Applied Networking Research Prizes from the Internet Engineering Task Force and a Google Research Scholar Award. She has also received a Commendation for Outstanding Teaching from Princeton’s School of Engineering and Applied Science for each of the past three years. She was named a Rising Star in Computer Networking and Communications by N2Women while in graduate school for uncovering key vulnerabilities in blockchain.