ZIUM attacks unlearned diffusion models by optimizing an image-captioning module that turns a target image into a text embedding, then reuses that module zero-shot on unseen images of the same unlearned concept.
Towards making systems for- get with machine unlearning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
ZIUM attacks unlearned diffusion models by optimizing an image-captioning module that turns a target image into a text embedding, then reuses that module zero-shot on unseen images of the same unlearned concept.