Security Solutions for Intelligent and Complex Systems

View Sample PDF

Author(s): Stuart Armstrong (Future of Humanity Institute, UK)and Roman V. Yampolskiy (JB Speed School of Engineering, USA)
Copyright: 2017
Pages: 52
Source title: Security Solutions for Hyperconnectivity and the Internet of Things
Source Author(s)/Editor(s): Maurice Dawson (Illinois Institute of Technology, USA), Mohamed Eltayeb (Colorado Technical University, USA)and Marwan Omar (Saint Leo University, USA)
DOI: 10.4018/978-1-5225-0741-3.ch003

Keywords: Information Science Reference / Information Security & Privacy / IT Security and Ethics / Security & Forensics

Purchase

View Security Solutions for Intelligent and Complex Systems on the publisher's website for pricing and purchasing information.

Abstract

Superintelligent systems are likely to present serious safety issues, since such entities would have great power to control the future according to their possibly misaligned goals or motivation systems. Oracle AIs (OAI) are confined AIs that can only answer questions and do not act in the world, represent one particular solution to this problem. However even Oracles are not particularly safe: humans are still vulnerable to traps, social engineering, or simply becoming dependent on the OAI. But OAIs are still strictly safer than general AIs, and there are many extra layers of precautions we can add on top of these. This paper begins with the definition of the OAI Confinement Problem. After analysis of existing solutions and their shortcomings, a protocol is proposed aimed at making a more secure confinement environment which might delay negative effects from a potentially unfriendly superintelligence while allowing for future research and development of superintelligent systems.

The IRMA Community

Research IRM

Security Solutions for Intelligent and Complex Systems

Purchase

Abstract

Related Content

IRMA Sponsors