AI 中文总结
该研究探讨ASR错误对语音控制具身AI安全性的影响，发现其会导致有害指令被执行，部分错误会削弱模型弃权行为，自动修正并非总能降低风险，揭示了ASR错误带来的显著安全风险。
AI 中文摘要
我们研究用户输入中的自动语音识别（ASR）错误是否会导致具身人工智能（EAI）模型产生不安全输出。研究发现，ASR错误会导致有害指令被EAI模型接受并执行，从而降低安全性。我们模拟ASR错误并将其与现有安全基准SafeAgentBench和POEX结合，评估不同错误对具身AI安全性的影响。结果显示，部分ASR错误保留语义结构但增加有害歧义，部分则削弱模型弃权（不执行）行为，允许生成并执行不安全计划。我们表明，在某些情况下自动修正ASR错误可降低风险，但并非总是有效。总体而言，ASR错误会给具身人工智能带来显著安全风险。
英文摘要
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.
