ロボットが聞き間違えるとき:音声操作型具現化AIの安全リスクのマッピング
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI
音声認識の誤りが具現化AIの安全な動作を損なうことを示し、誤りをシミュレートして安全ベンチマークで評価した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sihan Jia, Oliver Lemon
分類: cs.AI, cs.CL, cs.RO
原文アブストラクト
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.
