Skip to main navigation Skip to search Skip to main content

NSF Safe-OSE: Center for Security-Assuring AI Agent Communication and Interoperability Standard and the Open-Source Ecosystem

Project: Research

Abstract & Details

Description

Award ID: 2625398

Artificial intelligence (AI) agents are increasingly used in government services, business systems, research environments, and other digital infrastructure, yet they currently lack a safe and reliable way to communicate across different organizations and technologies. This project strengthens the Safety for OpenSource Ecosystems (SafeOSE) mission by improving the safety, security, and trustworthiness of the Natural Language Interaction Protocol (NLIP), an emerging open standard that enables AI agents to exchange structured messages. By enhancing the reliability of this communication layer, the project supports the national interest in secure and resilient digital infrastructure and reduces risks of unintended actions, data exposure, or system failures. The project also expands participation in opensource development by producing freely available tools and resources that help developers, educators, and organizations adopt safer AI systems. These improvements benefit society by making AIenabled services more dependable and easier to secure. The project will develop and evaluate security mechanisms that operate directly at the NLIP protocol layer, using NLIPs standardized message envelopes and control fields as enforcement points for validation, authorization, and policy constraints. The team will analyze vulnerabilities in agenttoagent and agenttouser communicationsuch as authorization weaknesses, session hijacking, costamplification misuse, memory poisoning, prompt injection, and semantic manipulationand design protocollevel mitigations that are generalizable across frameworks. Methods include implementing opensource security extensions, building validation and conformance tools, and testing protections across multiple realworld agent frameworks and enterprise systems. This unified approach enables consistent, crossplatform safeguards that are difficult to achieve when defenses are implemented separately within individual applications or vendors. The resulting tools, standardsaligned mechanisms, and evaluation results will advance the science of securing AImediated communication and strengthen the broader NLIP opensource ecosystem. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Florence Rabanal
StatusActive
Effective start/end date09/01/26 → 08/31/28

Lead and Sub-Awardee Organization(s)

Funding

  • (Safe-OSE) NSF Safety, Security, and Privacy of Open-Source Ecosystems: $1,500,000.00

Active Fiscal Year

  • FY2028
  • FY2027
  • FY2026

Start Fiscal Year

  • FY2026

TIP Programs

  • (Safe-OSE) NSF Safety, Security, and Privacy of Open-Source Ecosystems

Key Technology Areas

  • Super Intelligence
  • (confidence score: 100%)
  • Data and Cybersecurity
  • (confidence score: 100%)
  • Advanced Computing and Semiconductors
  • (confidence score: 93%)

Technology Foci

  • Data Privacy
  • (confidence score: 99%)
  • Distributed Ledger Technologies
  • (confidence score: 88%)
  • Cyber-security
  • (confidence score: 100%)
  • Machine Learning Training Data
  • (confidence score: 99%)
  • Advanced Computer Software
  • (confidence score: 88%)
  • Super Intelligence (excluding ML)
  • (confidence score: 98%)
  • Autonomy
  • (confidence score: 95%)

Congressional District at Award

  • District n. 13 of Illinois

Current Congressional District

  • District n. 13 of Illinois

United States

  • Illinois

Core Based Statistical Area (CBSA)

  • Champaign-Urbana, IL

County

  • County: Champaign, IL

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint. Learn more about Elsevier's Fingerprint Engine here: https://beta.elsevier.com/products/elsevier-fingerprint-engine