Description |
1 online resource (19 pages) : illustrations |
|
text txt rdacontent |
|
computer c rdamedia |
|
online resource cr rdacarrier |
Note |
In scope of the U.S. Government Publishing Office Cataloging and Indexing Program (C&I) and Federal Depository Library Program (FDLP). |
Bibliography |
Includes bibliographical references (pages 17-19). |
Contents |
Executive summary. -- Introduction. -- Why is AI security different? -- Who should read this document? -- Who is responsible for developing secure AI? -- Guidelines for secure AI system development. -- 1. Secure design. -- 2. Secure of development. -- 3. Secure deployment. -- 4. Secure operation and maintenance. -- Further reading. |
Summary |
This document recommends guidelines for providers of any systems that use artificial intelligence (AI), whether those systems have been created from scratch or built on top of tools and services provided by others. Implementing these guidelines will help providers build AI systems that function as intended, are available when needed, and work without revealing sensitive data to unauthorised parties. AI systems are subject to novel security vulnerabilities that need to be considered alongside standard cyber security threats. When the pace of development is high - as is the case with AI - security can often be a secondary consideration. Security must be a core requirement, not just in the development phase, but throughout the life cycle of the system. |
Note |
Description based on online resource; title from PDF title page (DOD web site, viewed Dec. 29, 2023). |
Subject |
Artificial intelligence -- Security measures -- Government policy -- International cooperation.
|
|
Intelligence artificielle -- Sécurité -- Mesures -- Politique gouvernementale -- Coopération internationale.
|
Added Author |
United States. Cybersecurity & Infrastructure Security Agency, author.
|
Added Title |
Guidelines for secure artificial intelligence system development. |
Gpo Item No. |
0520-K (online) |
Sudoc No. |
HS 2.2:AR 8 |
|