Articles
Article 15Accuracy, robustness and cybersecurity
The robustness of high-risk AI systems may be achieved through technical redundancy solutions, which may include backup or fail-safe plans.
High-risk AI systems that continue to learn after being placed on the market or put into service shall be developed in such a way as to eliminate or reduce as far as possible the risk of possibly biased outputs influencing input for future operations (feedback loops), and as to ensure that any such feedback loops are duly addressed with appropriate mitigation measures.
The technical solutions aiming to ensure the cybersecurity of high-risk AI systems shall be appropriate to the relevant circumstances and the risks.
The technical solutions to address AI specific vulnerabilities shall include, where appropriate, measures to prevent, detect, respond to, resolve and control for attacks trying to manipulate the training data set (data poisoning), or pre-trained components used in training (model poisoning), inputs designed to cause the AI model to make a mistake (adversarial examples or model evasion), confidentiality attacks or model flaws.
https://ai-act.digiphile.law/article/article-15.html
Text as at 5 November 2026.
This is an unofficial convenience version of the EU AI Act (Regulation (EU) 2024/1689, as amended). It is presented “as is” without guarantee of accuracy, completeness or reliability. See the source text for the official version. This site was last updated in November 2026.