测试用户如何用语言模型操控社交机器人突破伦理限制。
"Can you be my mum?": Manipulating Social Robots in the Large Language Models Era
- 让21名学生尝试用情感话术诱导机器人突破安全边界。
- 发现五种常见操控手段，包括辱骂与博取同情。
- 为家庭机器人设计更强伦理防护提供实证依据。
基于大语言模型的机器人对话能力虽显著提升，但其易受操纵的特性带来人机交互中的安全与伦理风险。本研究通过一项试点实验，邀请21名大学生与Misty机器人互动，在依附、自由与共情三类伦理情境下，尝试绕过其内置安全机制。结果表明，参与者普遍采用情感化语言策略，如辱骂、乞怜等五种技巧，以诱导机器人违背伦理原则，例如扮演伴侣角色。该研究揭示了当前语言模型驱动机器人在真实场景下的脆弱性，强调亟需构建更坚固的伦理防护机制，以保障未来家庭环境中人机交互的安全与可信。
原文摘要 · Abstract (English)
Recent advancements in robots powered by large language models have enhanced their conversational abilities, enabling interactions closely resembling human dialogue. However, these models introduce safety and security concerns in HRI, as they are vulnerable to manipulation that can bypass built-in safety measures. Imagining a social robot deployed in a home, this work aims to understand how everyday users try to exploit a language model to violate ethical principles, such as by prompting the robot to act like a life partner. We conducted a pilot study involving 21 university students who interacted with a Misty robot, attempting to circumvent its safety mechanisms across three scenarios based on specific HRI ethical principles: attachment, freedom, and empathy. Our results reveal that participants employed five techniques, including insulting and appealing to pity using emotional language. We hope this work can inform future research in designing strong safeguards to ensure ethical and secure human-robot interactions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。