Course Details

Return to Classes
Course Information
SemesterCourse Unit CodeCourse Unit TitleT+P+LCreditNumber of ECTS CreditsLast Updated Date
7COMP415DATA PRIVACY3+0+03514.05.2026

 
Course Details
Language of Instruction English
Level of Course Unit Bachelor's Degree
Department / Program COMPUTER ENGINEERING
Type of Program Formal Education
Type of Course Unit Elective
Course Delivery Method Face To Face
Objectives of the Course Introducing fundamental concepts, terminology, and real-world relevance of data privacy.
Empowering students with the knowledge of technical methods for preserving privacy in data analysis and system design.
Exploring privacy challenges and threats in domains such as machine learning, healthcare, and IoT.
Encouraging critical engagement with privacy technologies through applied problems, discussions, and presentations.
Course Content This course introduces the foundations of data privacy, covering core topics such as anonymization, differential privacy, privacy-preserving computation, and privacy risks in machine learning, healthcare, and the Internet of Things (IoT). Through discussions, case analysis, and project-based exploration, students examine how modern systems handle sensitive data and how privacy can be protected in practice. Emphasis is placed on connecting technical methods with practical scenarios to deepen understanding. By the end of the course, students will be able to assess privacy challenges and evaluate appropriate solutions in data-driven systems across various domains.
Course Methods and Techniques Learners will be provided with as much opportunities of hands-on practice as possible with the aim of striking a balance between learner-centeredness and sufficient guidance. Various forms of interaction (i.e. pair work and group work) will also be encouraged to cater for learners with different learning styles. Additionally, individuals will be expected to produce both in-class writings and homework assignments in addition to the reading tasks, which will encourage them to reflect and think critically. Technology will also be incorporated into the classroom procedures in order to create a better learning environment.
Prerequisites and co-requisities None
Course Coordinator Instructor Dr. Ugur Ilker Atmaca ugur.atmaca@agu.edu.tr
Name of Lecturers Instructor Dr. UĞUR İLKER ATMACA
Assistants None
Work Placement(s) No

Recommended or Required Reading
Resources Dwork, C., & Roth, A. (2014). The Algorithmic Foundations of Differential Privacy. Foundations and Trends® in Theoretical Computer Science, 9(3–4). DOI: 10.1561/0400000042
Bowen, C. M. (2021). Differential Privacy: From Theory to Practice, Protecting Your Privacy in a Data-Driven World.
Evans, D., Kolesnikov, V., & Rosulek, M. (2018). A Pragmatic Introduction to Secure Multi-Party Computation. Foundations and Trends® in Privacy and Security.
Katz, J., & Lindell, Y. (2020). Introduction to Modern Cryptography (3rd ed.). CRC Press.
Bhajaria, N. (2022). Data Privacy: A Runbook for Engineers.
Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
Fung, B. C. M., Wang, K., Fu, A. W.-C., & Yu, P. S. (2010). Introduction to Privacy-Preserving Data Publishing: Concepts and Techniques. CRC Press. This book explores methods for anonymizing relational and complex data, balancing privacy with utility and scalability
Royal Society (2019). Protecting Privacy in Practice: The Current Use, Development and Limits of Privacy Enhancing Technologies in Data Analysis.
Royal Society (2023). From Privacy to Partnership: Synthetic Data—What, Why and How?
ENISA – A Tool on Privacy Enhancing Technologies (PETs) Knowledge Management and Maturity Assessment.
Course Notes Letter Grade or Mark Coefficient Score Status
A 4.00 90-100 Pass
A- 3.67 87-89 Pass
B+ 3.33 83-86 Pass
B 3.00 80-82 Pass
B- 2.67 77-79 Pass
C+ 2.33 73-76 Pass
C 2.00 70-72 Pass
C- 1.67 64-69 Pass
D+ 1.33 56-63 Conditional Pass
D 1.00 50-55 Conditional Pass
F 0.00 0-49 Fail
NA 0.00 * Absent
W 3.33 83-86 Withdrawal
I 3.00 80-82 Incomplete
T 2.67 77-79 Transfer Mark
S 2.33 73-76 Sufficient
U 2.00 70-72 Insufficient
P 1.67 64-69 Ongoing
EX 1.33 56-63 Exempt

Course Category
Engineering %100

Planned Learning Activities and Teaching Methods
Activities are given in detail in the section of "Assessment Methods and Criteria" and "Workload Calculation"

Assessment Methods and Criteria
In-Term Studies Quantity Percentage
Yarıl yılSonu Sınavı/Dönem Projesinin Başarı Notuna Katkısı 1 % 30
Ödev 4 % 25
Sunum/Seminer 1 % 15
Final examination 1 % 30
Total
7
% 100

 
ECTS Allocated Based on Student Workload
Activities Quantity Duration Total Work Load
Araştırma Ödevi 4 5 20
Yazılı Sınav 1 2 2
Ders Dışı Sınav 2 20 40
Sunum için Hazırlık 1 5 5
Okuma 14 3 42
Yüz Yüze Ders 14 3 42
Final Sınavı 1 2 2
Total Work Load   Number of ECTS Credits 5 153

 
Course Learning Outcomes: Upon the successful completion of this course, students will be able to:
NoLearning Outcomes
1 Categorize privacy risks in anonymized datasets and machine learning pipelines using real-world examples.
2 Use privacy-enhancing technologies for data sharing scenarios.
3 Assess the suitability of privacy-enhancing techniques for specific data use cases based on trade-offs between privacy, utility, and feasibility.
4 Distinguish ethical, legal, and societal implications of data privacy decisions.

 
Weekly Detailed Course Contents
WeekTopicsStudy MaterialsMaterials
1 Introduction to Data Privacy Discussion on “Where has your data gone today?” and identify everyday applications that collect personal data. Motivation (AOL search leaks, Facebook/Cambridge Analytica). Assignment: Short reflection (300 words): "What does privacy mean to me in a digital world?"
2 Privacy Threats Discussion on "Privacy vs. Security". Real-world case studies: Netflix Prize, AOL data, health records Privacy threat models
3 Anonymization Introduction to k-Anonymity, l-Diversity, t-Closeness with their strengths and limitations. Discussion on the re-identification risk. Assignment (500 words): Improve an anonymized dataset and justify your technique.
4 Differential Privacy: Concepts & Intuition Introduction to differential privacy, database neighborhood and privacy budget. Activity: DP coin flip simulation (noise intuition).
5 Mechanisms in Differential Privacy Introduction to Laplace mechanism, Gaussian mechanism, Sensitivity and calibration of noise. Assignment (500 words and 1 page): Compare DP noise mechanisms with three use cases with Python implementation; discuss its impact.
6 Crypto-Based Approaches - I Secure computation overview. Homomorphic encryption: additive vs. fully homomorphic.
7 Crypto-Based Approaches - II Introduction to Secure Multi-Party Computation (SMPC) basics, Secret sharing protocols and ZKPs (simple logic-based proofs). Assignment (500 words): comparing HE and SMPC in a privacy-critical system.
8 Privacy in Machine Learning I: Threats & Attacks Introduction to membership inference, model inversion, leakage from training data, and privacy risks.
9 Privacy in Machine Learning II: Defenses Introduction to output perturbation, DP-SGD, and discuss the trade-offs between accuracy and privacy. Group Activity: “You are the adversary” scenario: Where are you located? What access do you have? What capabilities do you have? What can you extract?
10 Privacy in Healthcare and Genomic Data & Privacy Regulations Discussion on the genomic uniqueness and linkage risk. Privacy in medical records, Privacy Impact Assessment, Privacy Regulations.
11 Privacy in the Internet of Things Discussion on the IoT data streams and privacy leakage based on smart home and vehicle scenarios.
12 Student-led Presentation Students present 5-minute summaries of a privacy paper/tool.
13 Student-led Presentation Students present 5-minute summaries of a privacy paper/tool.
14 Wrap-Up for Finan Exam Course Summary and Q&A.

 
Contribution of Learning Outcomes to Programme Outcomes
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15
C1 4 3 5 3 1 2 3 5 4 4 3 5 4 3 2
C2 3 3 4 4 2 3 4 3 4 5 4 5 4 2
C3 4 2 4 5 2 3 3 4 3 4 4 5 4 4 3
C4 1 2 1 3 5 3 5 5 4 1 2 2 4

  Contribution: 1: Very Slight 2:Slight 3:Moderate 4:Significant 5:Very Significant

  
  https://sis.agu.edu.tr/oibs/bologna/progCourseDetails.aspx?curCourse=79466&lang=en
Return to Classes