15 citations · 26 across the 7 of their papers we have counts for
7 papers
A Reproducible Extraction of Training Images from Diffusion Models
Ryan Webster
Recently, Carlini et al. demonstrated the widely used model Stable Diffusion can regurgitate real training samples, which is troublesome from a copyright perspective. In this work,…
On the De-duplication of LAION-2B
Ryan Webster, Julien Rabin, Loic Simon +1
Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science. These models require large image d…
This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces
Ryan Webster, Julien Rabin, Loic Simon +1
Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website {\small \url{ http://this…
On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximity
Rodrigue Siry, Ryan Webster, Loic Simon +1
The recent advent of powerful generative models has triggered the renewed development of quantitative measures to assess the proximity of two probability distributions. As the scal…
Revisiting Precision and Recall Definition for Generative Model Evaluation
Loïc Simon, Ryan Webster, Julien Rabin
In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for ge…
Detecting Overfitting of Deep Generative Networks via Latent Recovery
Ryan Webster, Julien Rabin, Loic Simon +1
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not…
Innovative Non-parametric Texture Synthesis via Patch Permutations
Ryan Webster
In this work, we present a non-parametric texture synthesis algorithm capable of producing plausible images without copying large tiles of the exemplar. We focus on a simple synthe…