Skip to Content
CSE5519CSE5519 Advances in Computer Vision (Topic H: 2023: Safety, Robustness, and Evaluation of CV Models)

CSE5519 Advances in Computer Vision (Topic H: 2023: Safety, Robustness, and Evaluation of CV Models)

How to backdoor diffusion models

link to paper 

Tip

This is an interesting paper showing that it is possible to backdoor a diffusion model with high utility and high specificity at a low cost compared to per-training.

I wonder how this technique could possibly be used for AI watermarking and reliably detected with other AI operations?

And there are many metrics and loss functions used in this paper, I wonder what objectives they are trying to optimize, and looking for more clarification on the presentation.

Last updated on
CSE5519 Advances in Computer Vision (Topic J: 2022: Open-Vocabulary Object Detection)CSE5519 Advances in Computer Vision (Topic B: 2023: Vision-Language Models)