Date on Master's Thesis/Doctoral Dissertation

4-2021

Document Type

Master's Thesis

Degree Name

M. Eng.

Department

Computer Engineering and Computer Science

Degree Program

JB Speed School of Engineering

Committee Chair

Yampolskiy, Roman

Committee Co-Chair (if applicable)

Zhang, Wei

Committee Member

Kantardzic, Mehmed

Committee Member

Biro, Csaba

Author's Keywords

Artificial Intelligence; AI Safety; Normal Accident Theory; AI Alignment

Abstract

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated with AI applications. In addition, we also use AI safety principles to quantify the unique risks of increased intelligence and human-like qualities in AI. Together, these two fields give a more complete picture of the risks of contemporary AI. By focusing on system properties near accidents instead of seeking a root cause of accidents, we identify where attention should be paid to safety for current generation AI systems.

Download

Share

COinS