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.
Available: https://arxiv.org/abs/2408.03515
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
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.
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.