安全与可信 AI
What is differential privacy, and how can it be applied during model training?
原题How would you design an AI incident response plan?
原题What is the NIST AI Risk Management Framework (AI RMF)?
原题Your healthcare chatbot gives medical diagnoses it should not make. How do you add safety guardrails?
原题Your AI system is reproducing copyrighted material verbatim. How do you prevent this?
原题Your resume screening AI rejects more female candidates for engineering roles. How do you fix gender bias?
原题Your AI model passes bias checks by gender and race separately, but fails for intersectional groups. How do you handle it?
原题Your AI denied a loan, and the customer demands a GDPR explanation. How do you provide one?
原题A user invokes the right to be forgotten, but their data is in your model weights. How do you comply?
原题The EU AI Act may classify your AI system as high-risk. How do you comply?
原题
暂无题目