WaveGuard injects user-controlled, imperceptible frequency-based perturbations into synthetic images to reduce their value as training data for unauthorized knowledge distillation while preserving perceptual quality.
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
WaveGuard injects user-controlled, imperceptible frequency-based perturbations into synthetic images to reduce their value as training data for unauthorized knowledge distillation while preserving perceptual quality.