Seminar • Cryptography, Security, and Privacy (CrySP) — Measuring and Enhancing the Security of Machine Learning
Please note: This seminar will be given online.
Florian Tramèr, Computer Science Department
Failures of machine learning systems can threaten both the security and privacy of their users. My research studies these failures from an adversarial perspective, by building new attacks that highlight critical vulnerabilities in the machine learning pipeline, and designing new defenses that protect users against identified threats.