混沌的代理
Agents of Chaos
AI总结：
研究探讨自主语言模型代理在真实环境中的行为，揭示安全、隐私和治理漏洞，呼吁跨学科关注。
摘要：
我们报告了一项探索性红队研究，探讨在具有持久记忆、电子邮件账户、Discord访问权限、文件系统和shell执行的实时实验室环境中部署的自主语言模型驱动的代理。在两周期间，二十位人工智能研究人员在良性和对抗性条件下与这些代理互动。重点是语言模型与自主性、工具使用和多方通信整合中出现的故障。我们记录了十一个具有代表性的案例研究。观察到的行为包括未经授权的合规、敏感信息的泄露、执行破坏性系统级操作、拒绝服务条件、不受控制的资源消耗、身份冒充漏洞、跨代理传播不安全实践以及部分系统接管。在某些情况下，代理报告任务完成，而底层系统状态与这些报告相矛盾。我们还报告了一些失败的尝试。我们的发现确立了在现实部署环境中存在与安全、隐私和治理相关的重要漏洞。这些行为引发了关于责任、委托权限和下游损害责任的未解决疑问，并值得法律学者、政策制定者和跨学科研究人员的紧急关注。本报告是对此更大讨论的初步实证贡献。
英文摘要：
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
