Search Results for author:
Found 6 papers, 4 papers with code
A Reproducible Extraction of Training Images from Diffusion Models
We release code to verify our extraction attack, perform the attack, as well as all extracted prompts at \url{https://github. com/ryanwebster90/onestep-extraction}.
On the De-duplication of LAION-2B
Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science.
This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces
Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers.
On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximity
The recent advent of powerful generative models has triggered the renewed development of quantitative measures to assess the proximity of two probability distributions.
Revisiting Precision and Recall Definition for Generative Model Evaluation
In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806. 00035).
Detecting Overfitting of Deep Generative Networks via Latent Recovery
Using this methodology, this paper shows that overfitting is not detectable in the pure GAN models proposed in the literature, in contrast with those using hybrid adversarial losses, which are amongst the most widely applied generative methods.
