AI Engineer: AI System Design and Ethics Flashcards
6 cards from real AI practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 6 AI Engineer: AI System Design and Ethics flashcards as text
What is 'model governance' in enterprise AI system design?
Answer: Policies, controls, and oversight processes that manage the AI model lifecycle from development to retirement
Model governance encompasses approval workflows, audit trails, risk assessments, and accountability structures ensuring AI models are developed and used responsibly.
What is 'adversarial robustness' in AI system design?
Answer: A model's ability to maintain correct behavior when inputs are deliberately manipulated to cause errors
Adversarial robustness measures how well a model resists adversarial examples — subtly perturbed inputs crafted to fool the model while appearing normal to humans.
What is the primary challenge addressed by 'federated learning' in AI?
Answer: Training AI models across decentralized devices without sharing raw data, preserving privacy
Federated learning trains models locally on each device and aggregates only model updates (not raw data), enabling collaboration without centralizing sensitive data.
What is 'AI red-teaming'?
Answer: Adversarial testing where experts try to find failures, vulnerabilities, and harmful behaviors in AI systems
AI red-teaming involves deliberately probing a system for safety failures, harmful outputs, or exploitable behaviors before deployment, mimicking adversarial users.
What does 'scalable oversight' aim to solve in AI alignment research?
Answer: Maintaining meaningful human supervision of AI as systems become more capable than the humans overseeing them
Scalable oversight addresses how to keep humans in meaningful control of AI decisions when the AI may eventually be more capable than the humans evaluating it.
What is 'impact assessment' in the context of deploying an AI system?
Answer: A structured evaluation of potential risks, harms, and societal consequences before an AI system goes live
An AI impact assessment proactively identifies potential harms (bias, privacy risks, safety issues) and affected stakeholders before a system is deployed.