A trimming-based attack that selects the most important pixels or patches via Monte Carlo point-wise evaluation outperforms prior sparse and patch attacks on ImageNet.
Mind the box: l\_1 -apgd for sparse adversarial attacks on image classifiers
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
-
Sparse patches adversarial attacks via extrapolating point-wise information
A trimming-based attack that selects the most important pixels or patches via Monte Carlo point-wise evaluation outperforms prior sparse and patch attacks on ImageNet.