VideoPure is a diffusion-based adversarial purification framework that combines temporal DDIM inversion, spatial-temporal optimization, and multi-step voting to defend video recognition models.
Only once attack: Fooling the tracker with adversarial template,
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
-
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
VideoPure is a diffusion-based adversarial purification framework that combines temporal DDIM inversion, spatial-temporal optimization, and multi-step voting to defend video recognition models.