CSC 533 Privacy in the Digital Age
3 Credit Hours
Privacy is a growing concern in our modern society. We interact and share our personal information with a wide variety of organizations, including financial and healthcare institutions, web service providers and social networks. Many times such personal information is inappropriately collected, used or shared, often without our awareness. This course introduces privacy in a broad sense, with the aim of providing students an overview of the challenging and emerging research topics in privacy.
Prerequisite
Prerequisites: CSC 316 (ST 370 is recommended).
Informal: You need to have some understanding on (1) basic concepts on statistics and probability and (2) basics of systems implementation (e.g., web, distributed systems, networking, etc.). If you do not have a basic understanding of these areas, you may have difficulty with certain parts of the course. If you have questions regarding these prerequisites, please contact the instructor.
Course Overview
This course will expose students to many of the issues that privacy engineers, program managers, researchers and designers deal with in industry. ST 370 is recommended but not mandatory.
- By the end of the course, students will learn about the following areas in privacy:
- Data privacy: the motivations for data privacy and common implementations (e.g., k-anonymity, differential privacy).
- Online privacy: online tracking and anonymous communication systems.
- Opportunities and challenges of applying AI/ML for privacy.
- Side-channel threats: Emerging side-channel attacks.
- Privacy acts: privacy regulations, frameworks and compliance/auditing tools.
- Usable privacy: perceptions of privacy, privacy attitudes, privacy preferences.
Course Outcomes
By the end of this course, students will be able to:
- Execute data deanonymization attack
- Apply techniques to anonymize personally identifiable information (PII) in databases
- Generate differentially private responses
- Apply private information retrieval (PIR) scheme
- Distinguish and filter online tracking traffic
- Contrast different online tracking techniques
- Explain how anonymous communication networks work and how they help users preserve their online anonymity
- Demonstrate privacy attacks on machine learning models
- Design privacy-preserving federated learning
- Compute statistical parity for machine learning models
- Contrast privacy regulations
- Design usable privacy policy template
- Compare and contrast users’ attitudes and perceptions of privacy
Course Requirements
The course will consist of exams, home assignments (worst graded one will be dropped) and a course project.
| Homework | 35% |
| Pop quizzes | 5% |
| Course Project | 10% |
| Midterm Exam | 25% |
| Final Exam | 25% |
Textbook
This course has no formal textbook. The course readings will come from online book chapters, seminal papers, and other informative sources. Slides will serve as the main reading resource summarizing the lecture content.
Here are some useful online books that provide additional information:
- Carmela Troncoso Privacy and Online Rights
- Lazar et al. Research Methods in Human-Computer Interaction
- Daniel Solove. Understanding Privacy
- Daniel J. Solove and Paul M. Schwartz. Consumer Privacy and Data Protection
- Helen Nissenbaum. Privacy in Context
Updated 4/25/2025