NSF Safe Learning-Enabled Systems Program for Provably Safe and Robust AI

NSF Safe Learning-Enabled Systems Program for Provably Safe and Robust AI is sponsored by U.S. National Science Foundation (NSF), in partnership with Open Philanthropy and Good Ventures. This program supports foundational research ensuring that learning-enabled and AI systems are safe with high levels of confidence.

Safe Learning-Enabled Systems | NSF - U.S. National Science Foundation Safe Learning-Enabled Systems Archived funding opportunity This document has been archived. Important information for proposers and award recipients All proposals must be submitted in accordance with the requirements specified in the funding opportunity and in the Proposal & Award Policies & Procedures Guide (PAPPG) and its supplements .

All NSF grants and cooperative agreements are subject to the applicable set of NSF award terms and conditions . NSF has updated its research security policies for NSF funded projects. Supports research into the design and implementation of safe learning-enabled systems in which safety is ensured with high levels of confidence.

As artificial intelligence (AI) systems rapidly increase in size, acquire new capabilities, and are deployed in high-stakes settings, their safety becomes extremely important. Ensuring system safety requires more than improving accuracy, efficiency, and scalability: it requires ensuring that systems are robust to extreme events, and monitoring them for anomalous and unsafe behavior.

The objective of the Safe Learning-Enabled Systems program, which is a partnership between the National Science Foundation, Open Philanthropy and Good Ventures, is to foster foundational research that leads to the design and implementation of learning-enabled systems in which safety is ensured with high levels of confidence.

While traditional machine learning systems are evaluated pointwise with respect to a fixed test set, such static coverage provides only limited assurance when exposed to unprecedented conditions in high-stakes operating environments. Verifying that learning components of such systems achieve safety guarantees for all possible inputs may be difficult, if not impossible.

Instead, a system’s safety guarantees will often need to be established with respect to systematically generated data from realistic (yet appropriately pessimistic) operating environments. Safety also requires resilience to “unknown unknowns”, which necessitates improved methods for monitoring for unexpected environmental hazards or anomalous system behaviors, including during deployment.

In some instances, safety may further require new methods for reverse-engineering, inspecting, and interpreting the internal logic of learned models to identify unexpected behavior that could not be found by black-box testing alone, and methods for improving the performance by directly adapting the systems’ internal logic.

Whatever the setting, any learning-enabled system’s end-to-end safety guarantees must be specified clearly and precisely. Any system claiming to satisfy a safety specification must provide rigorous evidence, through analysis corroborated empirically and/or with mathematical proof.

Program Director, CISE/IIS Program Director, CISE/CCF Program Director, CISE/CNS Program Director, CISE/CCF April 5, 2023 - Safe Learning-Enabled Systems (NSF 23-562) Webinar Additional program resources Frequently Asked Questions for Safe Learning-Enabled Systems (NSF 23-562) Awards made through this program Browse projects funded by this program Map of recent awards made through this program Directorate for Computer and Information Science and Engineering (CISE) Division of Information and Intelligent Systems (CISE/IIS) Division of Computing and Communication Foundations (CISE/CCF) Division of Computer and Network Systems (CISE/CNS)