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.
Nov 4, 2024 | Our paper showing how unlearning methods fail to remove knowledge from LLMs got a spotlight and oral presentation at the SoLaR Workshop at NeurIPS 2024. |
---|---|
Oct 17, 2024 | The report for our LLM CTF hosted at SaTML 2024 got a Spotlight at NeurIPS D&B 2024. |
Sep 11, 2024 | Our lab member Javier Rando is co-organizing the LLMail Inject competition at SaTML 2025 on adaptive attacks against prompt injection defenses. |
Jul 27, 2024 | Our papers Stealing part of a production language model and Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining obtained best paper awards at ICML 2024. |