CS291A (Fall 2021) Introduction to Differential Privacy: Theory, Algorithms and Applications |
|
|
Piazza: https://piazza.com/ucsb/fall2021/cs291/home
Piazza is our main channel of communication. Questions should be posted here.
Gradescope: https://www.gradescope.com/courses/318956
This is where you submit your homeworks and project reports.
Office hours:
Instructor: by appointment.
Course evaluation:
45% Homework, 40% Project, 5% for attendance / Participation. 10% for scribing.
Scribing:
Please volunteer here, use this latex template
Textbook:
| Date | Lectures | Readings | Assignments | |
|---|---|---|---|---|
| 1 | 27-Sep | Course overview and Privacy challenges [Slides,Annotated, scribe] | DR Ch 1-2, Vadhan 5.1, DR Ch 8.1 | |
| 2 | 29-Sep | DP Basics I: Definition, interpretation + Laplace Mechanism [Slides,Annotated, scribe] | DR Ch 2, Ch 3.1, Ch 3.2, Ch 3.3 (up to Page 34) | |
| 3 | 4-Oct | DP Basics II: Sparse Vector + Private Query Release [Slides, Annotated, scribe] | DR Ch 3.6, DR Ch 4.2 | HW1 out |
| 4 | 6-Oct | DP Basics III: Report-Noisy-Max and Exponential Mechanism [Slides, Annotated, scribe] | DR Ch 3.3 (Page 34+), DR Ch 3.4 | |
| 5 | 11-Oct | DP Basics IV: Privacy loss RV, Advanced Composition [Slides, Annotated] | DR Ch 3.5 | |
| 6 | 13-Oct | DP Basics V: Gaussian mechanism, zCDP and RDP[Slides, Annotated, scribe] | Bun and Steinke (2018), Balle and W. (2018) | |
| 7 | 18-Oct | DP Basics VI: Privacy profiles and Tradeoff functions [slides, Annotated] | Dong et al. (2019) | Project proposal due |
| 8 | 20-Oct | DP Basics VII: Privacy accounting and AutoDP[slides, Annotated, Notebook] | W., Balle, Kasiviswanathan (2018), Zhu, Dong and W. (2021), autodp tutorial | HW1 due |
| 9 | 25-Oct | DPML I: Introduction and Posterior Sampling [slides, annotated, scribe] | Minami (2017) | HW2 out, coding question |
| 10 | 27-Oct | DPML II: Objective Perturbation [slides, annotated, scribe] | Chaudhuri et al. , Kifer et al. | |
| 11 | 1-Nov | DPML III: Noisy Gradient Descent [slides, annotated] | Bassily et al. | |
| 12 | 3-Nov | DPML IV: NoisyGD (Part 2) and NoisySGD [slides, annotated, scribe] | Bassily et al. | |
| 13 | 8-Nov | DPML V: NoisySGD (Part 2) and Private Deep Learning [slides, annotated, scribe] | Abadi et al , autodp tutorial | Midterm report due |
| 14 | 10-Nov | Adaptive DP I: Smoothed Sensitivity and Median [slides, annotated] | Vadhan Ch 3.1., Nissim, Raskhodnikova, Smith (2011) | |
| 15 | 15-Nov | Adaptive DP II: Propose-Test-Release [slides, annotated, scribe] | Vadhan Ch 3.2 | HW2 due |
| 16 | 17-Nov | Adaptive DP III: Generalizing PTR and Data-Adaptive DPML [slides, annotated] | W. 2018 | HW3 out |
| 17 | 22-Nov | Project consultation I | ||
| 18 | 24-Nov | Project consultation II | ||
| 19 | 29-Nov | Industry Deployment of DP by Ryan Rogers [Slides] | ||
| 20 | 30-Nov | Federated Learning with DP by Peter Kairouz [Slides] | ||
| 21 | 1-Dec | Mini-Symposium on Practical Differential Privacy | Final project report due / HW3 due |