# A Response to Glaze Purification via IMPRESS

arXiv: https://arxiv.org/abs/2312.07731 · HTML: https://mlsanity.com/paper/2312.07731/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2023.

## Built on by (most cited first, 2 of 2)

- [Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss](https://mlsanity.com/paper/2403.16728/) (2024)
- [GLEAN: Generative Learning for Eliminating Adversarial Noise](https://mlsanity.com/paper/2409.10578/) (2024)

## Abstract (arXiv)

Recent work proposed a new mechanism to remove protective perturbation added by Glaze in order to again enable mimicry of art styles from images protected by Glaze. Despite promising results shown in the original paper, our own tests with the authors' code demonstrated several limitations of the proposed purification approach. The main limitations are 1) purification has a limited effect when tested on artists that are not well-known historical artists already embedded in original training data, 2) problems in evaluation metrics, and 3) collateral damage on mimicry result for clean images. We believe these limitations should be carefully considered in order to understand real world usability of the purification attack.