Expert Survey: AI Reliability & Security Research Priorities
Joe O'Brien, Jeremy Dolan, Jay Kim, Jonah Dykhuizen, Jeba Sania, Sebastian Becker, Jam Kraprayoon, Cara Labrador

TL;DR
This survey of 53 experts identifies key research priorities in AI reliability and security, providing a data-driven ranking to guide strategic investment and ensure safe, beneficial AI development.
Contribution
It is the first study to quantify expert priorities across a comprehensive AI safety taxonomy and produce impact-based rankings for research directions.
Findings
Identified top research areas with highest potential impact.
Provided a ranked list of AI safety and security research priorities.
Guided strategic resource allocation for AI reliability and security.
Abstract
Our survey of 53 specialists across 105 AI reliability and security research areas identifies the most promising research prospects to guide strategic AI R&D investment. As companies are seeking to develop AI systems with broadly human-level capabilities, research on reliability and security is urgently needed to ensure AI's benefits can be safely and broadly realized and prevent severe harms. This study is the first to quantify expert priorities across a comprehensive taxonomy of AI safety and security research directions and to produce a data-driven ranking of their potential impact. These rankings may support evidence-based decisions about how to effectively deploy resources toward AI reliability and security research.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEthics and Social Impacts of AI · Information and Cyber Security · Adversarial Robustness in Machine Learning
