STO-Activities: (no title)
Activity title:
AI Assurance & Security
Activity Reference:
IST-215
Panel:
IST
Security Classification:
NATO UNCLASSIFIED
Status:
Active
Activity type:
RTG
Start date:
2024-04-15T00:00:00Z
Actual End date:
2027-04-15T00:00:00Z
Keywords:
Artificial Intelligence AI, assurance, equitability, framework, interpretability, Machine Learning ML, reliability and robustness, responsible use, security
Background:
NATO has recognized Artificial Intelligence (AI) as the foundational technology that will affect the full spectrum of activities undertaken by the Alliance. The current NATO AI Strategy is fourfold:
• To provide a foundation for NATO and Allies to lead by example and encourage the development and use of AI in a responsible manner for Allied defense and security purposes.
• To accelerate and mainstream AI adoption in capability development and delivery, enhancing interoperability within the Alliance, including through proposals for AI Use Cases, new structures, and new programs.
• To protect and monitor our AI technologies and ability to innovate, addressing security policy considerations such as the operationalization of our Principles of Responsible Use.
• To identify and safeguard against the threats from malicious use of AI by state and non-state actors.
To address the above objectives, IST ET-125 Evolving Threat Landscape for Coalition AI/ML Systems was formed in March 2023 with the goal of fostering an enduring collaborative community of NATO R&D organizations and industry partners to shape future NATO AI security and assurance capabilities. IST ET-125 has active participation and ongoing contribution from government and industry members from over 10 nations and NATO Bodies.
Objectives:
Building on the success of IST ET-125, the new RTG will continue to: (i) leverage existing coalition AI security & assurance capabilities; (ii) share protected threat intelligence, vulnerability data and real-world attack; (iii) shape exemplar shared use cases; (iv) build defensive and mitigation techniques; (v) develop red teaming capabilities and exercises.
Topics:
The group is interested in on the following topics:
• AI Assurance / Responsible AI / Trustworthy AI / Safe AI
• AI Security / AI Red Teaming / Adversarial Machine Learning
• AI Robustness / AI Resiliency
• AI Assurance Frameworks, Standards, Terminology, and Metrics
• AI Risk and Vulnerability Assessment, including AI Incident Sharing
• AI Risk Mitigation
• AI Equitability / AI Fairness / Privacy Protecting (or Privacy Enhanced) AI
Specifically, the group will initially focus collaborative research activities around several lines of effort (LOE’s) with designated national/NATO leads:
• LOE 1: Foundational Concepts for AI Assurance (USA lead)
• LOE 2: Recommendations for Assured AI Use (NCIA lead)
• LOE 3: AI Security Gaps and Threats (NLD lead)
• LOE 4: IST-210 RSY AI Security and Assurance for Military Systems (USA lead)
Contact:
Open2Partners:
Title:
Created at 17/10/2023 14:00 by System Account
Last modified at 16/05/2024 07:00 by System Account
Go back to list
Home(NATO STO)