The Secure and Private AI (SPY) Lab conducts research on the security, privacy and trustworthiness of machine learning systems.
We often approach these problems from an adversarial perspective, by designing attacks that probe the worst-case performance of a system to ultimately understand and improve its safety.
News
| Apr 15, 2026 | Our lab member Edoardo Debenedetti will be presenting at the Real World AI Security conference at Stanford this June. Several lab members will also be attending. Come find us there! |
|---|---|
| May 12, 2025 | AgentDojo, a benchmark from our group to evaluate robustness of AI agents, has been awarded the first prize in the SafeBench competition. |
| May 10, 2025 | 2 papers from our group were accepted to ICML 2025 as spotlights! Check our publications page for details. |
People
Florian Tramèr
Faculty
Avital Shafran
Postdoc
Edoardo Debenedetti
PhD Student
Daniel Paleka
PhD Student
Javier Rando
PhD Student
Michael Aerni
PhD Student
Jie Zhang
PhD Student
Kristina Nikolić
PhD Student
Lukas Fluri
PhD Student
