Preserving the privacy of AI training data
Amazon Science
Researchers demonstrated that machine learning models trained on sensitive data can leak information about their training datasets through inference attacks, federated learning gradient reconstruction, and shared global models. Specific defenses include differential privacy (which adds calibrated noise during training, achieving 78% accuracy at privacy budget ε=1.5 versus 90% without privacy protection) and secure multiparty computation (which successfully prevented reconstruction of training samples in experiments). Organizations deploying models on private financial, healthcare, or proprietary data must now implement these technical mitigations to comply with regulations like HIPAA and GDPR.
Why it matters
How we reproduced three attacks that extract private training data from AI models and the cryptographic defenses that stop them.
