LVLM-based agents exhibit trust boundary confusion with visual injections and a multi-agent defense separating perception from decision-making reduces misleading responses while preserving correct ones.
Scenetap: Scene-coherent typographic adversarial planner against vision-language models in real-world environ- ments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
LVLM-based agents exhibit trust boundary confusion with visual injections and a multi-agent defense separating perception from decision-making reduces misleading responses while preserving correct ones.