The history of robotics and artificial intelligence in many ways is also the history of humanity’s attempts to control such technologies. From the Golem of Prague to the military robots of modernity, the debate continues as to what degree of independence such entities should have and how to make sure that they do not turn on us, its inventors. Numerous recent advancements in all aspects of research, development and deployment of intelligent systems are well publicized but safety and security issues related to AI are rarely addressed. This book is proposed to mitigate this fundamental problem. It is comprised of chapters from leading AI Safety researchers addressing different aspects of the AI control problem as it relates to the development of safe and secure artificial intelligence. The book is the first edited volume dedicated to addressing challenges of constructing safe and secure advanced machine intelligence.

The chapters vary in length and technical content from broad interest opinion essays to highly formalized algorithmic approaches to specific problems. All chapters are self-contained and could be read in any order or skipped without a loss of comprehension.

part I|2 pages

Concerns of Luminaries

chapter 1|18 pages

Why the Future Doesn't Need Us

ByBill Joy

chapter 2|26 pages

The Deeply Intertwined Promise and Peril of GNR

ByRay Kurzweil

chapter 3|9 pages

The Basic AI Drives

ByStephen M. Omohundro

chapter 4|13 pages

The Ethics of Artificial Intelligence

ByNick Bostrom, Eliezer Yudkowsky

chapter 5|4 pages

Friendly Artificial Intelligence

The Physics Challenge
ByMax Tegmark

chapter 6|14 pages

MDL Intelligence Distillation

Exploring Strategies for Safe Access to Superintelligent Problem-Solving Capabilities
ByK. Eric Drexler

chapter 7|9 pages

The Value Learning Problem

ByNate Soares

chapter 8|14 pages

Adversarial Examples in the Physical World

ByAlexey Kurakin, Ian J. Goodfellow, Samy Bengio

chapter 9|14 pages

How Might AI Come About?

Different Approaches and Their Implications for Life in the Universe
ByDavid Brin

chapter 10|18 pages

The MADCOM Future

How Artificial Intelligence Will Enhance Computational Propaganda, Reprogram Human Culture, and Threaten Democracy … and What can be Done About It
ByMatt Chessen

chapter 11|20 pages

Strategic Implications of Openness in AI Development

ByNick Bostrom

part II|1 pages

Responses of Scholars

chapter 13|7 pages

AI Safety

A First-Person Perspective
ByEdward Frenkel

chapter 14|9 pages

Strategies for an Unfriendly Oracle AI with Reset Button

ByOlle Häggström

chapter 15|8 pages

Goal Changes in Intelligent Agents

BySeth Herd, Stephen J. Read, Randall O'Reilly, David J. Jilk

chapter 16|10 pages

Limits to Verification and Validation of Agentic Behavior

ByDavid J. Jilk

chapter 17|14 pages

Adversarial Machine Learning

ByPhillip Kuznetsov, Riley Edmunds, Ted Xiao, Humza Iqbal, Raul Puri, Noah Golmant, Shannon Shih

chapter 18|13 pages

Value Alignment via Tractable Preference Distance

ByAndrea Loreggia, Nicholas Mattei, Francesca Rossi, K. Brent Venable

chapter 19|10 pages

A Rationally Addicted Artificial Superintelligence

ByJames D. Miller

chapter 20|17 pages

On the Security of Robotic Applications Using ROS

ByDavid Portugal, Miguel A. Santos, Samuel Pereira, Micael S. Couceiro

chapter 21|24 pages

Social Choice and the Value Alignment Problem *

ByMahendra Prasad

chapter 22|23 pages

Disjunctive Scenarios of Catastrophic AI Risk

ByKaj Sotala

chapter 23|18 pages

Offensive Realism and the Insecure Structure of the International System

Artificial Intelligence and Global Hegemony
ByMaurizio Tinnirello

chapter 24|18 pages

Superintelligence and the Future of Governance

On Prioritizing the Control Problem at the End of History
ByPhil Torres

chapter 25|19 pages

Military AI as a Convergent Goal of Self-Improving AI

ByAlexey Turchin, David Denkenberger

chapter 26|15 pages

A Value-Sensitive Design Approach to Intelligent Agents

BySteven Umbrello, Angelo F. De Bellis

chapter 27|11 pages

Consequentialism, Deontology, and Artificial Intelligence Safety

ByMark Walker

chapter 28|8 pages

Smart Machines ARE a Threat to Humanity

ByKevin Warwick