art_15__para_5__para__2
AI Act
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.
← art_15__para_5__para · All articles · doc__heading__3__para__11 →
Source: EUR-Lex CELLAR · retrieved 2026-08-26 · Text as adopted (Official Journal); later amendments are not incorporated in this text.