A unified threat model for LLM-enabled robots reveals three cross-boundary attack chains from user input to unsafe physical actuation due to missing validations and unmediated crossings.
Image-based prompt injection: Hijacking multimodal llms through visually embed- ded adversarial instructions
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
-
From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems
A unified threat model for LLM-enabled robots reveals three cross-boundary attack chains from user input to unsafe physical actuation due to missing validations and unmediated crossings.