Article

On the Robustness Tradeoff in Fine-Tuning

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs

Systematic Evaluation of Geolocation Privacy Mechanisms

Securing Cloud File Systems using Shielded Execution

Privacy-Preserving Protocols for Smart Cameras and Other IoT Devices