AdViT generates adversarial images that make ViT classifiers misclassify while keeping attribution maps nearly identical to benign inputs, with high white-box success and useful black-box transferability after genetic-algorithm tuning.
Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
AdViT generates adversarial images that make ViT classifiers misclassify while keeping attribution maps nearly identical to benign inputs, with high white-box success and useful black-box transferability after genetic-algorithm tuning.