Week 13: Privacy in ML Pipelines and Trade-Offs, plus Exam 3

Dates: Apr 5-9  ·  Reading: Handout 11: Privacy-Preserving ML and Trade-Offs

Learning Objectives

Monday Session

Privacy-preserving ML: differential privacy, federated learning, and encrypted computation. Security versus privacy: why stronger encryption can make detection harder. Real-world dilemmas.

Wednesday Session

Exam 3 (online, non-cumulative, covers Weeks 10-13). Quiz 10 administered the same week.

Lab

Lab 11: Differential Privacy. Implement a simple differential privacy mechanism that adds noise before training, and see the privacy/accuracy trade-off.

Quiz / This Week

Quiz 10. Privacy-preserving ML; differential privacy; federated learning; security vs. privacy trade-offs.


← All lecture notes  ·  Detailed slides and notes are filled in with the lecture-builder skill.