口絵
本標準について
The Artificial Intelligence Security Verification Standard (AISVS) is a community-driven catalogue of testable security requirements for AI-enabled systems. It gives data scientists, MLOps engineers, software architects, developers, testers, security professionals, tool vendors, regulators, and consumers a common language for specifying security controls across the AI lifecycle, from data collection and model development to deployment, monitoring, and retirement, so that organizations can measure and improve the resilience, privacy, and safety of their AI solutions.
Every requirement in AISVS has been developed from the ground up to reflect the AI threat landscape. While AISVS draws inspiration from broader security best practices (including the OWASP ASVS), it is purpose-built for artificial intelligence systems and complements (rather than duplicates) governance frameworks such as NIST AI RMF and ISO/IEC 42001.
著作権とライセンス
Version 1.0 (Working Draft), 2025
Copyright © 2025-2026 The AISVS Project.
Creative Commons Attribution-ShareAlike 4.0 International License の下で公開されています。 再利用または配布する場合には、本著作物のライセンス条項を他者に対して明確に伝える必要があります。
プロジェクトリーダー
Jim Manico
Otto Sulin
Aras "Russ" Memisyazici
執筆者とレビュー担当者
The following individuals have contributed to the AISVS through requirements authoring, review, or technical feedback:
Last updated