Course syllabus for Data privacy

Course syllabus adopted 2025-02-20 by Head of Programme (or corresponding).

Overview

  • Swedish nameIntegritetsskydd för personuppgifter
  • CodeDAT655
  • Credits7.5 Credits
  • OwnerMPCSC
  • Education cycleSecond-cycle
  • Main field of studyComputer Science and Engineering
  • DepartmentCOMPUTER SCIENCE AND ENGINEERING
  • GradingTH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail

Course round 1

  • Teaching language English
  • Application code 42128
  • Maximum participants50
  • Open for exchange studentsNo

Credit distribution

0125 Laboratory 3 c
Grading: UG		 3 c
0225 Examination 4.5 c
Grading: TH		 4.5 c

In programmes

Examiner

Eligibility

General entry requirements for Master's level (second cycle)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.

Specific entry requirements

English 6 (or by other approved means with the equivalent proficiency level)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.

Course specific prerequisites

90 hp points in courses in Computer Science and/or Mathematics or equivalent. Among those courses, the student should have:
• 5.0 hp in calculus
• 7.5 hp on Statistical Methods for Data Science or equivalent.
• 7.5 hp on A course in functional programming or programming with Python, or equivalents

Aim

In an era where data is one of our most valuable assets, data privacy has become an essential aspect of technology. This course explores the fundamental principles, technologies, and practical techniques required to protect personal information in data-driven environments. Through a blend of theoretical knowledge and hands-on assignments, this course will equip students with the tools to both understand and implement data privacy measures effectively, especially in contexts where data anonymization and privacy guarantees are critical.

Learning outcomes (after completion of the course the student should be able to)

Knowledge and understanding:
• Summarize the principles behind privacy laws like GDPR
• Identify data-sharing challenges with a focus on preserving privacy, including anonymization techniques and their vulnerabilities.
• Explain Differential Privacy (DP) theoretical foundations and their properties.
• Develop practical systems and tools for implementing DP.
• Use synthetic data algorithms and describe their challenges, privacy guarantees, and utility.

Skills and abilities:
• Critically analyze privacy risks in data-sharing scenarios and evaluate the strengths and weaknesses of anonymization techniques and DP.
• Design and develop systems employing DP techniques.
• Test DP mechanisms and analyze their statistical soundness using established methods.
• Create synthetic data, understanding the trade-offs between data utility and privacy guarantees

Judgement ability and approach:
• Assess privacy-preserving systems and frameworks, considering the trade-offs between utility and privacy.
• Evaluate the choice of privacy-preserving techniques based on the context, considering both the theoretical guarantees and practical limitations of mechanisms like k-anonymity and differential privacy.
• Discern the ethical implications of data privacy, and align their solutions with legal frameworks like the GDPR, helping with compliance in real-world scenarios.

Content

The course is divided into two sub-courses: theory and assignments. The theory aspects will cover
  1. GDPR Principles
  2. Traditional Anonymization Techniques
  3. Differential Privacy (DP)
  4. System Building and Testing Using DP
  5. Synthetic Data Using DP
There will be assignments during the course, and the course is expected to use several programming languages in the lectures and the assignments, e.g., Haskell and Python.

Organisation

The course will be conducted primarily through traditional lectures and support activities like office hours to guide students in elaborating assignments.

Students will be expected to:
Attend lectures to grasp core topics, participate in discussions or in-class activities, and complete assignments.

Lecture attendance is highly recommended to fully understand the material, though it may not be compulsory.
Assignments will be compulsory and are essential for demonstrating the ability to apply the knowledge gained.

Literature

The literature is based on a main textbook, research articles, and complementary textbooks. The course literature will be available for students eight weeks before the start of the course.

Examination including compulsory elements

The course will be assessed through two main components:

Written Exam: A written exam will be conducted at the end of the course – this is the main examination. The exam will cover both the understanding and application of the concepts given in the course. There will be one re-examination for the exam.

Assignments: Throughout the course, students must complete a series of compulsory assignments graded as pass or fail. The assignments must be passed during the course, and they can be resubmitted for another assessment opportunity in the next instance of the course, where they will be assessed quickly.

The final grade of the course is the grade of the final exam according to the scale Fail (U) or Pass (3, 4, 5)

The course examiner may assess individual students in other ways than what is stated above if there are special reasons for doing so, for example if a student has a decision from Chalmers about disability study support.