Guidelines for Artificial Intelligence Containment
Guidelines for Artificial Intelligence Containment
复制标题
人工智能遏制指南
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Roman V Yampolskiy
中科院分区：
文献类型：
--
作者：
James Babcock;János Kramár;Roman V Yampolskiy
随着人工智能的能力几乎每天都在提高，开发供人工智能研究界使用的安全软件比以往任何时候都更加重要。基于我们之前关于人工智能遏制问题的工作，我们提出了一些指导方针，这些指导方针应该有助于人工智能安全研究人员为各级智能程序开发可靠的沙盒软件。这种安全容器软件将使研究和分析智能人工代理成为可能，同时保持一定的安全性，防止容器内部的信息泄露、社会工程攻击和网络攻击。
With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.