Summary of Regeneration Based Training-free Attribution Of Fake Images Generated by Text-to-image Generative Models, By Meiling Li et al.
Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models
by Meiling Li, Zhenxing Qian, Xinpeng Zhang
First submitted to arxiv on: 3 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 paper presents a training-free method for attributing fake images generated by text-to-image models to their source models. This is achieved by reconstructing the textual prompt of an image and then regenerating candidate images using different models, ranking them based on similarity to the test image. The approach allows model owners to be held accountable for any misuse of their models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper shows how to stop fake images generated by text-to-image models from being misused by attributing them to their source models. It does this without needing special training and can work with many different models. The method is good at detecting where an image came from, even if the image has been changed a bit. |
Keywords
» Artificial intelligence » Prompt
