most citedExtracting Training Data from Diffusion Models

100 citations · 136 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20235 cited

Unlocking Accuracy and Fairness in Differentially Private Image Classification

Leonard Berrada, Soham De, Judy Hanwen Shen +6

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework…

cs.LG202315 cited

Differentially Private Diffusion Models Generate Useful Synthetic Images

Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal +7

The ability to generate privacy-preserving synthetic versions of sensitive image datasets could unlock numerous ML applications currently constrained by data availability. Due to t…

cs.LG202314 cited

Tight Auditing of Differentially Private Machine Learning

Milad Nasr, Jamie Hayes, Thomas Steinke +5

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mech…

cs.CR2023100 cited

Extracting Training Data from Diffusion Models

Nicholas Carlini, Jamie Hayes, Milad Nasr +6

Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images. In this w…

cs.CR20222 cited

Reconstructing Training Data with Informed Adversaries

Borja Balle, Giovanni Cherubin, Jamie Hayes

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who…