Reference 3 stops to get here
Differential Privacy
A mathematical framework for quantifying and limiting privacy loss when releasing information about datasets.
Your route here
3 stops · basics first
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Training Data ✓ understood
The examples a model learns its weights from, kept separate from the validation and test data used to check how well it generalizes.
- Privacy-Preserving ML ✓ understood
Techniques for training and deploying models while protecting individual privacy (federated learning, differential privacy).
- Differential Privacy · you are here ✓ understood
Where it sits
Before this
Privacy-Preserving ML Differential Privacy
Leads to
Nothing yet: a destination in its own right.
Explore nearby
Shipping AI Federated Learning Training models across decentralized devices holding local data, without exchanging the data itself, preserving privacy. Shipping AI Membership Inference Determining if a specific example was in the training dataset, a privacy concern. Shipping AI Homomorphic Encryption Encryption allowing computation on encrypted data, enabling private model inference. Shipping AI Secure Multi-Party Computation Protocols allowing parties to jointly compute functions while keeping inputs private. Shipping AI Model Inversion Attacks that reconstruct training data or private information from model parameters or outputs.