CAGE attack aligns perturbations with token compression to achieve lower robust accuracy on compressed LVLMs than baseline attacks across mechanisms and datasets.
② Outer-LLMapproaches perform token selection or aggregationbeforethe main language model computation, treating the LLM as a black box
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.