Machine Learning and Cryptography

Cryptography offers a playbook for building trust on untrusted platforms. This research theme applies that playbook to modern machine learning, and aims to draw the contours of a new field at the Crypto X ML interface and identify concrete problems in trustworthy ML that benefit from cryptographic thinking and techniques. We study how cryptographic modeling and tools can endow ML systems with privacy, verifiability, and reliability.

For more, see my slides from a TCC 2025 talk.