Model Integrity when Unlearning with T2I Diffusion Models

Understand

The rapid advancement of text-to-image Diffusion Models has led to their widespread public accessibility.

• However these models, trained on large internet datasets, can sometimes generate undesirable outputs.
• To mitigate this, approximate Machine Unlearning algorithms have been proposed to modify model weights to reduce the generation of specific types of images, characterized by samples from a ``forget distribution'', while preserving the model's ability to generate other images, characterized by samples from a ``retain distribution''.
• While these methods aim to minimize the influence of training data in the forget distribution without extensive additional computation, we point out that they can compromise the model's integrity by inadvertently affecting generation for images in the retain distribution.