Core

Differential Privacy

Differential privacy is a mathematical guarantee that the output of a computation barely changes whether or not any single person's record was included, so an attacker studying the output cannot confidently tell who was in the data. You buy this guarantee by adding calibrated random noise, and you pay for it in accuracy. The privacy budget epsilon sets the exchange rate; smaller epsilon means more noise and more privacy, and a value like epsilon = 8 is moderate, not strong.

a free account unlocks the core curriculum tier · no card

RELATED CONCEPTS

PII Handling and Redaction Federated Learning AI Governance (SOC2, EU AI Act)

PRACTICE THIS IN REAL QUESTIONS

AI Security, Privacy & GovernanceHow would you defend a RAG system against poisoned retrieved context and vector/embedding attacks?→System Design & Production EngineeringYour product deploys into dozens of customer environments. Design secrets management across all of them.→AI Security, Privacy & GovernanceCompare PII detection methods, regex, entropy, NER, external APIs. Why can't regex alone find a person's name?→RAG & Agent System DesignA customer wants to expose internal APIs to a model via MCP. Design it safely: auth, least privilege, versioning.→AI Security, Privacy & GovernanceDesign a PII redaction system for an LLM pipeline, PII enters at user input, retrieved context, tool results, and output. Guard all four.→AI Security, Privacy & GovernancePrompts and outputs contain personal data. What does GDPR mean for each call to an external LLM endpoint?→