DIN EN 18282:2026-06
Artificial intelligence - Cybersecurity specifications for AI Systems; English version prEN 18282:2026 / Note: Date of issue 2026-05-15
| Fecha edición: |
2026-06-01
En Vigor
|
|---|---|
| Idiomas disponibles: | Inglés |
| Resumen: | This document addresses organizational and technical solutions aimed at ensuring the cybersecurity of high-risk AI systems over the lifecycle, appropriate to the relevant circumstances and the risks. The technical solutions to address AI specific vulnerabilities include, where appropriate, measures to prevent, detect, respond to, resolve and control for attacks trying to manipulate the training dataset (data poisoning), or pre-trained components used in training (model poisoning), inputs designed to cause the model to make a mistake (adversarial examples or model evasion), confidentiality attacks or model flaws. This document provides objective criteria to enable decisions on whether a given technical or organizational solution adequately achieves a given vulnerability-related goal. |
| Keywords: | Artificial intelligence|Attack|Confidentiality|Cyber security|Definitions|Documentation|Examination (quality assurance)|Information technology|IT security|Machine learning|Manipulation|Models|Neuronal networks|Risk|Safety|Safety measures|Specification|Specification (approval)|Systems|Threat|Weak points|Weakest point analysis |
| ICS: | 35.240.01 - Aplicaciones de las tecnologías de la información en general, 35.030 - Seguridad de la TI |
| CTN: |
Normas citadas
Libros relacionados
Normas relacionadas
Colecciones temáticas relacionadas
