Article 55(1)(a)
CurrentConditional timingEvaluate and Adversarially Test GPAI Models With Systemic Risk
Applies to GPAI Provider; Systemic-Risk GPAI.
- Actors
- GPAI Provider
- AI class
- Systemic-Risk GPAI
- Themes
- Risk & Assurance
Tracker Guidance
Perform model evaluation using state-of-the-art standardised protocols and tools, including conducting and documenting adversarial testing to identify and mitigate systemic risks.
Official text
(a) perform model evaluation in accordance with standardised protocols and tools reflecting the state of the art, including conducting and documenting adversarial testing of the model with a view to identifying and mitigating systemic risks;
Timing depends on the system
- 2 Aug 2025 — GPAI model placed on the market on or after 2025-08-02
- 2 Aug 2027 — GPAI model placed on the market before 2025-08-02