M-IFGSM, a masked iterative FGSM attack on CLIP, reduces top-1 accuracy to 12.5% on training renders and 35.4% on test renders of 3D Gaussian Splatting models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects
M-IFGSM, a masked iterative FGSM attack on CLIP, reduces top-1 accuracy to 12.5% on training renders and 35.4% on test renders of 3D Gaussian Splatting models.