Back to the Academy
AI

How a model fails, and who answers for it

Data poisoning, adversarial examples, model inversion, silent drift, proxy discrimination: nine ways an artificial intelligence system goes wrong, and what each one does to the risk of whoever runs it.

9 questions · 11 min · Intermediate

Certification available

Answer 80% of the questions correctly and the Academy issues you a named certification, carrying a number and verifiable online by a third party.

1 / 9

Most firms in a sector hand their risk analysis to the same foundation model. A flaw in that model's reasoning produces identical, simultaneous wrong decisions across the whole sector. What has this situation destroyed?

Revision

Every question, its answer and the reasoning

Every answer and its explanation appears here once you have finished the path. Each one then links to the matching glossary entry, where the concept is set out in full with its worked example.