How do I stop an AI system from leaking personal or sensitive data?
Answered
Control what data the model can access, prefer approaches that preserve user access controls (for example RAG/in-context learning), and apply additional security controls when using organisational data.
From the guidance
Primary (how) AI Playbook for the UK Government
Section: Working with your organisational data
Read this in AI Playbook for the UK Government (opens in new tab)
Related questions
- What is data poisoning in an AI system?
- Can I use AI to process personal data? Lawful, ethical and responsible use
- Can I rely on consent to process personal data in an AI system? Lawful, ethical and responsible use
- Can I reuse existing personal data to train or run an AI system? Lawful, ethical and responsible use
- What does data-protection fairness require of an AI system? Lawful, ethical and responsible use