Artificial intelligence safety and security /
edited by Roman V. Yampolskiy, Computer Engineering and Computer Science, Speed School of Engineering, University of Louisville.
- First edition.
- xxix, 443 pages : illustrations ; 25 cm.
- Chapman & Hall/CRC artificial intelligence and robotics series .
Chapter 1: Why the Future Doesn’t Need Us (Page-1), Chapter 2: The Deeply Intertwined Promise and Peril of GNR (Page-21),Chapter 3: The Basic AI Drives (Page-47),Chapter 4: The Ethics of Artificial Intelligence (Page-57),Chapter 5: Friendly Artificial Intelligence: The Physics Challenge (Page-71),Chapter 6: MDL Intelligence Distillation: Exploring Strategies for Safe Access to Superintelligent Problem-Solving Capabilities (Page-75),Chapter 7: The Value Learning Problem (Page-89),Chapter 8: Adversarial Examples in the Physical World (Page-99),Chapter 9: How Might AI Come About?: Different Approaches and Their Implications for Life in the Universe (Page-113),Chapter 10: The MADCOM Future: How Artificial Intelligence Will Enhance Computational Propaganda, Reprogram Human Culture, and Threaten Democracy … and What can be Done About It (Page-127),Chapter 11: Strategic Implications of Openness in AI Development (Page-145),Chapter 12: Using Human History, Psychology, and Biology to Make AI Safe for Humans (Page-167),Chapter 13: AI Safety: A First-Person Perspective (Page-199),Chapter 14: Strategies for an Unfriendly Oracle AI with Reset Button (Page-207),Chapter 15: Goal Changes in Intelligent Agents (Page-217),Chapter 16: Limits to Verification and Validation of Agentic Behavior (Page-225),Chapter 17: Adversarial Machine Learning (Page-235),Chapter 18: Value Alignment via Tractable Preference Distance (Page-249),Chapter 19: A Rationally Addicted Artificial Superintelligence (Page-263),Chapter 20: On the Security of Robotic Applications Using ROS (Page-273),Chapter 21: Social Choice and the Value Alignment Problem (Page-291), Chapter 22: Disjunctive Scenarios of Catastrophic AI Risk (Page-315),Chapter 23: Offensive Realism and the Insecure Structure of the International System: Artificial Intelligence and Global Hegemony (Page-339),Chapter 24: Superintelligence and the Future of Governance: On Prioritizing the Control Problem at the End of History (Page-357),Chapter 25: Military AI as a Convergent Goal of Self-Improving AI (Page-375),Chapter 26: A Value-Sensitive Design Approach to Intelligent Agents (Page-395), Chapter 27: Consequentialism, Deontology, and Artificial Intelligence Safety (Page-411),Chapter 28: Smart Machines ARE a Threat to Humanity (Page-423).