Summary of Fakeinversion: Learning to Detect Images From Unseen Text-to-image Models by Inverting Stable Diffusion, By George Cazenavette et al.
FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion
by George Cazenavette, Avneesh Sud, Thomas Leung, Ben Usman
First submitted to arxiv on: 12 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
Summary difficulty | Written by | Summary |
---|---|---|
High | Paper authors | High Difficulty Summary Read the original abstract here |
Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed synthetic image detector utilizes features obtained by inverting a pre-trained Stable Diffusion model to generalize well across unseen generators of high visual fidelity. Trained on lower-fidelity fake images generated via Stable Diffusion, the detector achieves new state-of-the-art performance across multiple training and evaluation setups. The detection approach is based on the idea that the inversion features from the open-source pre-trained Stable Diffusion model can be used to identify synthetic images. This detector is capable of detecting high-fidelity text-to-image models such as DALL-E 3, even when trained only on lower fidelity fake images. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to detect synthetic images using features from an open-source Stable Diffusion model. The detector is trained on fake images generated by this model and can recognize high-quality fake images made with other models like DALL-E 3. This method does better than previous detectors in many tests. |
Keywords
» Artificial intelligence » Diffusion » Diffusion model