CAGE attack aligns perturbations with token compression to achieve lower robust accuracy on compressed LVLMs than baseline attacks across mechanisms and datasets.
Attention score is not all you need for token importance indicator in KV cache reduction: Value also matters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
CAGE attack aligns perturbations with token compression to achieve lower robust accuracy on compressed LVLMs than baseline attacks across mechanisms and datasets.