Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings
Abstract
Foundation models could eventually introduce several pathways for undermining state security: accidents, inadvertent escalation, unintentional conflict, the proliferation of weapons, and the interference with human diplomacy are just a few on a long list. The Confidence-Building Measures for Artificial Intelligence workshop hosted by the Geopolitics Team at OpenAI and the Berkeley Risk and Security Lab at the University of California brought together a multistakeholder group to think through the tools and strategies to mitigate the potential risks introduced by foundation models to international security. Originating in the Cold War, confidence-building measures (CBMs) are actions that reduce hostility, prevent conflict escalation, and improve trust between parties. The flexibility of CBMs make them a key instrument for navigating the rapid changes in the foundation model landscape. Participants identified the following CBMs that directly apply to foundation models and which are further explained in this conference proceedings: 1. crisis hotlines 2. incident sharing 3. model, transparency, and system cards 4. content provenance and watermarks 5. collaborative red teaming and table-top exercises and 6. dataset and evaluation sharing. Because most foundation model developers are non-government entities, many CBMs will need to involve a wider stakeholder community. These measures can be implemented either by AI labs or by relevant government actors.
Cite
@article{arxiv.2308.00862,
title = {Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings},
author = {Sarah Shoker and Andrew Reddie and Sarah Barrington and Ruby Booth and Miles Brundage and Husanjot Chahal and Michael Depp and Bill Drexel and Ritwik Gupta and Marina Favaro and Jake Hecla and Alan Hickey and Margarita Konaev and Kirthi Kumar and Nathan Lambert and Andrew Lohn and Cullen O'Keefe and Nazneen Rajani and Michael Sellitto and Robert Trager and Leah Walker and Alexa Wehsener and Jessica Young},
journal= {arXiv preprint arXiv:2308.00862},
year = {2023}
}