Toward managing catastrophic AI risks

Artificial intelligence (AI) has rapidly improved over the past decade, leading to widespread adoption of AI systems and demonstrating the potential for AI to greatly benefit society. However, as with any powerful new technology, AI introduces risks that must be managed to fully realize these benefits. Recent breakthroughs in the generality of AI systems have drawn increased attention to AI risks, including those of a potentially catastrophic nature. To help manage these anticipated risks, we take a defense in depth approach, combining different areas of AI safety research to address different aspects of AI risk. We present research on making AI systems more robust to adversarial influence, monitoring AIs for hidden behavior and trojans, enabling AIs to understand and adhere to human values, and finally addressing systemic problems to enable increased transparency.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2024

Author dc:creator

• Mazeika, Mantas

Contributors dc:contributor

• Forsyth, David
• Li, Bo
• Lazebnik, Svetlana
• Krueger, David

• Ai Safety
• Ai Risk
• Robustness
• Red Teaming
• Neural Trojans
• Trojan Detection
• Alignment
• Model Stealing

Statement dc:rights

• Copyright 2024 Mantas Mazeika

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/124375

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F124375