Stop showing it the image.
Naive deletion continues training on the images that remain. But a model can still remember an image it has already learned, even when that image is no longer in its training data.
DATA UNLEARNING IN DIFFUSION MODELS
What happens when we ask a model to unlearn an image?
Explore the research, one fine-tuning step at a time.
A closer look at SISS through published image reconstructions and measured results.
About this experimentTHE INTERACTIVE EXPERIMENT
The model reconstructs the training face.
Published frame after 60 fine-tuning steps.
Published reconstructions of a noisy face. This is a figure walkthrough, not a live model run.
Final method averages across six faces, after 60 steps · Table 1
Target similarity SSCD
Overall model quality FID
These metrics stay fixed for each method. The timeline changes the image frame; the paper does not report per-step similarity scores.
BEHIND THE IMAGES
Naive deletion continues training on the images that remain. But a model can still remember an image it has already learned, even when that image is no longer in its training data.
SISS balances retaining useful model behavior with discouraging reconstruction of selected training images. Importance sampling makes this update more efficient.
These reconstructions don’t establish that every influence is erased, that it can never return, or that other copies of a model have changed.
In that separate experiment, the success criterion was no memorized outputs among 16 samples for a tested prompt, together with a quality threshold. See page 10 of the paper.
GO TO THE SOURCE
Alberti, Hasanaliyev, Shah & Ermon · Data Unlearning in Diffusion Models · ICLR 2025.
Image frames: Figure 3. Reported metrics: Table 1, page 7.