A task-agnostic attack that perturbs attention and embeddings of CLIP/ViT backbones degrades classification, retrieval, captioning, segmentation, and depth estimation without using labels or text.
Under- standing robustness of transformers for image classification
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Attacking Attention of Foundation Models Disrupts Downstream Tasks
A task-agnostic attack that perturbs attention and embeddings of CLIP/ViT backbones degrades classification, retrieval, captioning, segmentation, and depth estimation without using labels or text.