Confidence-Building Measures for Artificial Intelligence: Workshop proceedings
📰 OpenAI News
OpenAI workshop discusses confidence-building measures for artificial intelligence to mitigate potential risks to international security
Action Steps
- Identify potential risks introduced by foundation models to international security
- Develop and implement confidence-building measures such as crisis hotlines, incident sharing, and model transparency
- Establish collaborative relationships between AI labs, government actors, and other stakeholders
- Share datasets and evaluation metrics to improve trust and understanding
Who Needs to Know This
AI researchers, policymakers, and security experts can benefit from understanding confidence-building measures to reduce hostility and improve trust between parties in the development and deployment of foundation models
Key Insight
💡 Confidence-building measures can help mitigate the potential risks of foundation models to international security by improving trust and reducing hostility between parties
Share This
🚀 Confidence-building measures for AI can reduce risks to international security #AI #Security
Key Takeaways
OpenAI workshop discusses confidence-building measures for artificial intelligence to mitigate potential risks to international security
Full Article
# Confidence-Building Measures for Artificial Intelligence: Workshop proceedings | OpenAI
[Skip to main content](https://openai.com/index/confidence-building-measures-for-artificial-intelligence#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
August 1, 2023
[Conclusion](https://openai.com/research/index/conclusion/)[Safety](https://openai.com/news/safety-alignment/)
# Confidence-Building Measures for Artificial Intelligence: Workshop proceedings
[Read paper(opens in a new window)](https://arxiv.org/abs/2308.00862)
Loading…
Share
## 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.
* [Ethics & Safety](https://openai.com/research/index/?tags=ethics-safety)
* [Reasonings & Policy](https://openai.com/research/index/?tags=reasoning-policy)
* [Community & Collaboration](https://openai.com/research/index/?tags=community-collaboration)
## Report authors, in order of contribution
Sarah Shoker (OpenAI)*, Andrew Reddie (University of California, Berkeley)**
## Report authors, in alphabetical order
Sarah Barrington (University of California, Berkeley)
Ruby Booth (Berkeley Risk and Security Lab)
Miles Brundage (OpenAI)
Husanjot Chahal (OpenAI)
Michael Depp (Center for a New American Security)
Bill Drexel (Center for a New American Security)
Ritwik Gupta (University of California, Berkeley)
Marina Favaro (Anthropic)
Jake Hecla (University of California, Berkeley)
Alan Hickey (OpenAI)
Margarita Konaev (Center for Security and Emerging Technology)
Kirthi Kumar (University of California, Berkeley)
Nathan Lambert (Hugging Face)
Andrew Lohn (Center for Security and Emerging Technology)
Cullen O'Keefe (OpenAI)
Nazneen Rajan
[Skip to main content](https://openai.com/index/confidence-building-measures-for-artificial-intelligence#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
August 1, 2023
[Conclusion](https://openai.com/research/index/conclusion/)[Safety](https://openai.com/news/safety-alignment/)
# Confidence-Building Measures for Artificial Intelligence: Workshop proceedings
[Read paper(opens in a new window)](https://arxiv.org/abs/2308.00862)
Loading…
Share
## 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.
* [Ethics & Safety](https://openai.com/research/index/?tags=ethics-safety)
* [Reasonings & Policy](https://openai.com/research/index/?tags=reasoning-policy)
* [Community & Collaboration](https://openai.com/research/index/?tags=community-collaboration)
## Report authors, in order of contribution
Sarah Shoker (OpenAI)*, Andrew Reddie (University of California, Berkeley)**
## Report authors, in alphabetical order
Sarah Barrington (University of California, Berkeley)
Ruby Booth (Berkeley Risk and Security Lab)
Miles Brundage (OpenAI)
Husanjot Chahal (OpenAI)
Michael Depp (Center for a New American Security)
Bill Drexel (Center for a New American Security)
Ritwik Gupta (University of California, Berkeley)
Marina Favaro (Anthropic)
Jake Hecla (University of California, Berkeley)
Alan Hickey (OpenAI)
Margarita Konaev (Center for Security and Emerging Technology)
Kirthi Kumar (University of California, Berkeley)
Nathan Lambert (Hugging Face)
Andrew Lohn (Center for Security and Emerging Technology)
Cullen O'Keefe (OpenAI)
Nazneen Rajan
DeepCamp AI