Reza Shokri

6

Papers

158

Total Citations

Papers (6)

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Low-Cost High-Power Membership Inference Attacks

Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent

Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy