AI Research Centre

Safety, trust and explainability

At the AI Centre approaches are being developed to ensure the transparency and reliability of decisions made by AI, particularly in critical areas such as governance, medicine, and law. Specialists are creating verification tools for the libraries and modules used, ensuring the absence of vulnerabilities and the safe integration of AI into essential infrastructure components. Simultaneously, the team is working on methods to protect against potential abuses of AI technologies, preventing their use for unlawful purposes.

Safe AI: Algorithmic Provision and Tools

Tasks

Practical results

Effects