Jamie Hayes

Publications by Year

Research Areas

Adversarial Robustness in Machine Learning, Privacy-Preserving Technologies in Data, Topic Modeling, Ethics and Social Impacts of AI, Cryptography and Data Security

Most-Cited Works

• → Extracting Training Data from Diffusion Models(2023)96 cited
• → Local and Central Differential Privacy for Robustness and Privacy in Federated Learning(2020)33 cited
• → Unlocking High-Accuracy Differentially Private Image Classification through Scale(2022)33 cited
• → Differentially Private Diffusion Models Generate Useful Synthetic Images(2023)15 cited
• → Tight Auditing of Differentially Private Machine Learning(2023)14 cited
• → Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice(2025)5 cited
• → Unlocking Accuracy and Fairness in Differentially Private Image Classification(2023)4 cited
• → Bounding Training Data Reconstruction in DP-SGD(2023)3 cited
• → Reconstructing Training Data with Informed Adversaries(2022)2 cited
• → Learning to be adversarially robust and differentially private(2022)2 cited