Hidden Tail crafts adversarial images that force VLMs to emit long invisible runs of special tokens, inflating output length up to 19.2x while keeping the visible answer normal.
The Multi-Modal Fusion in Visual Ques- tion Answering: A Review of Attention Mechanisms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
Hidden Tail crafts adversarial images that force VLMs to emit long invisible runs of special tokens, inflating output length up to 19.2x while keeping the visible answer normal.