5 · Applied & production AI

18. Safety, Ethics and Governance

Bias, privacy, evaluation harnesses, red-teaming and the regulatory landscape.

9 min read · 3 MCQs

Bias and fairness

Models inherit the biases in their training data. Measure per-group performance, document intended use and known limits in a model card, and treat an unexplained gap between slices as a defect, not a statistic.

Privacy and security

Minimise personal data, scrub it at ingestion, and remember that anything in a prompt may be logged. Threats include training-data extraction, membership inference, model theft via distillation, and prompt injection through retrieved content.

Evaluation and governance

Ship an automated eval suite — golden questions, regression cases, adversarial prompts — and run it on every model or prompt change. Red-team before launch. Regimes such as the EU AI Act tier obligations by risk, requiring documentation, human oversight and transparency for higher-risk uses.

Chapter quiz

3 questions · pass mark 75%
  1. 1. A model card documents…

  2. 2. Membership inference attacks try to determine…

  3. 3. Risk-tiered obligations are the core idea of…

Answer every question to submit. Progress for ai-18 is saved in this browser.