Approaches include data minimization, differential privacy, secure computation, local processing, access controls, and retention limits. Each protects a different threat model and may trade off utility, cost, or complexity.
Privacy-preserving machine learning uses technical and operational methods to reduce exposure of sensitive data during training or inference.
Approaches include data minimization, differential privacy, secure computation, local processing, access controls, and retention limits. Each protects a different threat model and may trade off utility, cost, or complexity.