When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI

2026-08-28

AI Summary

研究探讨了语音识别错误对实体AI安全的影响，通过模拟这些错误并结合现有安全基准进行评估，发现某些错误增加语义模糊性或削弱模型拒绝行为，导致安全隐患。

Abstract

We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them preserve semantic structure but increase harmful ambiguity, while others weaken the model refusal behaviour and allow unsafe plans to be generated and executed. We show that in some cases automatic correction of ASR errors can reduce the risk, but this is not always effective. Overall, we show that ASR errors lead to significant safety risks for embodied AI.

Problem

• Automatic Speech Recognition
• Embodied AI
• Safety Risks

Innovation

• Automatic Speech Recognition (ASR) Errors
• Embodied AI Safety
• Semantic Ambiguity
• Model Refusal Behavior