ETSI EN 304 223 - Securing AI (SAI)

What ETSI EN 304 223 - Securing AI (SAI) requires

European telecommunications standards for mitigating attacks against AI models, including data poisoning, model evasion, and supply chain vulnerabilities.

Pillar: Cybersecurity · Authority: European Telecommunications Standards Institute (ETSI) · Version: 1.1.1 · Last updated: 2026-07-01

Primary source: https://www.etsi.org/deliver/etsi_en/304200_304299/304223/

SHA-256 integrity: 4259fef0a38f3c48af4ab6334acc47aaf2a80a4d41357e6eba753485422d0705

Primary Citations — 6 traced to source

• ETSI EN 304 223: Securing Artificial Intelligence (SAI); Baseline Cyber Security Requirements for AI Models and Systems (V2.1.1, 2025)
• OWASP Machine Learning Security Top 10 (ML01: Input Manipulation).

+ 4 more citations (full bibliography, deterministic workflow, actionable schema and crosswalks) included in the vault unlock — $0.01 via Skyfire / L402 / Direct Base USDC.

Access

• Discovery (free): /api/v1/nodes/etsi-en-304-223-sai.json — 6-field metadata
• Vault (full node): /api/v1/vault/nodes/etsi-en-304-223-sai.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
• Canonical URL: https://bidda.com/intelligence/etsi-en-304-223-sai
• Back to registry: Browse all 10,085 compliance nodes