BlackCAtt creates smaller, explainable black-box attacks on object detectors by targeting minimal causal pixel sets, outperforming or matching standard methods and acting as a meta-algorithm when combined with them.
Square attack: a query-efficient black-box adversarial attack via random search
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
ATAC boosts CLIP robustness to adversarial image changes by correcting embeddings via augmentation-induced drift vectors and angular consistency checks, beating prior test-time methods by nearly 50 percent on average with low overhead.
citing papers explorer
-
Out-of-the-box: Black-box Causal Attacks on Object Detectors
BlackCAtt creates smaller, explainable black-box attacks on object detectors by targeting minimal causal pixel sets, outperforming or matching standard methods and acting as a meta-algorithm when combined with them.
-
ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
ATAC boosts CLIP robustness to adversarial image changes by correcting embeddings via augmentation-induced drift vectors and angular consistency checks, beating prior test-time methods by nearly 50 percent on average with low overhead.