Guidelines for Artificial Intelligence Containment

📖 Description

1 Guidelines for Artificial Intelligence Containment James Babcock Cornell University [email removed] Janos Kramar University of Montreal [email removed] Roman V. Yampolskiy University of Louisville [email removed] Abstract 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 progr ams 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 con tainer. Keywords: AI Boxing, AI Containment, AI Confinement!, AI Guidelines , AI Safety , ...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1707.08476