An Inversion-based Measure of Memorization for Diffusion Models

원문 초록

The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are vulnerable to training data memorization, raising concerns regarding copyright infringement and privacy invasion. This study delves into a rigorous analysis of memorization in diffusion models. We introduce an inversion-based measure of memorization, InvMM, which searches for a sensitive latent noise distribution accounting for the replication of an image. For accurate estimation of the memorization score, we propose an adaptive algorithm that balances the normality and sensitivity of the inverted distribution. Comprehensive experiments, conducted on both unconditional and text-guided diffusion models, demonstrate that InvMM is capable of detecting heavily memorized images and elucidating the effect of various factors on memorization. Additionally, we discuss how memorization differs from membership. In practice, InvMM serves as a useful tool for model developers to reliably assess the risk of memorization, thereby contributing to the enhancement of trustworthiness and privacy-preserving capabilities of diffusion models.