A prompting defense that learns per-class phase and amplitude Fourier prompts and weights them by robust accuracy improves adversarial robustness of frozen classifiers.
Amplitude-phase recombination: Rethinking robustness of convolutional neural networks in frequency domain
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
-
Improving Adversarial Robustness via Phase and Amplitude-aware Prompting
A prompting defense that learns per-class phase and amplitude Fourier prompts and weights them by robust accuracy improves adversarial robustness of frozen classifiers.