Denoising-PGD attack exposes shared adversarial samples across non-blind, blind, plug-and-play and unfolding denoisers, yielding a robustness similitude metric that ranks data-driven non-blind models as most robust.
Explaining and harnessing adversarial examples,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
Denoising-PGD attack exposes shared adversarial samples across non-blind, blind, plug-and-play and unfolding denoisers, yielding a robustness similitude metric that ranks data-driven non-blind models as most robust.