vissza a tantárgylistához   nyomtatható verzió    

    Privacy-Preserving Technologies

    A tantárgy neve magyarul / Name of the subject in Hungarian: Személyes adatok védelme

    Last updated: 2025. szeptember 9.

    Budapest University of Technology and Economics
    Faculty of Electrical Engineering and Informatics

    Electrical Engineering,
    Engineering Information Technology,

    Elective course
    Course ID Semester Assessment Credit Tantárgyfélév
    VIHIAV35   2/0/0/f 2  
    3. Course coordinator and department Pejó Balázs,
    4. Instructors Dr. Balázs Pejó, Assistant professor, Department of Networked Systems and Services
    6. Pre-requisites
    Ajánlott:

    7. Objectives, learning outcomes and obtained knowledge This course provides an introduction into the practical problems of data protection and privacy. Students can develop skills of understanding and assessing privacy threats and designing countermeasures. The course focuses on the problem of unwanted personal and sensitive data leakage from different information sources (e.g., large datasets, web-tracking, encrypted traffic, machine learning models, etc.), and its detection as well as mitigations using Privacy Enhancing Technologies (PETS). The objective of the course is to provide skills needed by Data Protection Officers (DPO) and required by the European General Data Protection Regulation (GDPR). 
    8. Synopsis 1. week: Introduction (Motivation, Highlights, Examples)
    2. week: Dark Patterns (Types, Countermeasures, Cognitive Biases)
    3. week: Tracking (Profiling, Data Brokers, Web Tracking, Fingerprinting)
    4. week: Hidden Data (Sensitive information inference, data brokers, manipulation)
    5. week: GDPR (Personal / Sensitive Data, Principles , Lawfulness of Data Processing)
    6. week: Machine Learning (Inference / Reconstruction / Poisoning / Backdoors / Fairness)
    7. week: ((Un)Structured) Data Deanonymization (Uniqueness, Inference, Fingerprinting)
    8. week: (Aggregated) Data Deanonymization (Query Auditing, Location Reidentification)
    9. week: Anonymization (Synthetic Data, K-Anonimity, Ad-hoc Methods)
    10. week: Differential Privacy (Definitions, Properties, Sensitivity, Methods, Libraries)
    11. week: Cryptography (Basics, HE, SMPC, OT, SS, PSI, PIR, ZKP, FE, PQC)
    12. week: Cryptography (Secure Messaging, Mixnets, Tor, Cryptocurrencies, E-Voting)
    13. week : Exam
    14. week: Extra Class (Exam Retake / Repeat Cancelled Lecture)

    9. Method of instruction Lectures
    10. Assessment Passing the mid-term exam requires achieving at least 50% of the total available points. The final semester grade is calculated based on the total score from the mid-term exam and any additional points earned during the semester. The extra points are 10% of the exam; they can be obtained via a homework. Without the extra points the best grade can also be achieved. 


    11. Recaps During the semester, there is an opportunity to retake the mid-term exams. An unsuccessful retake can be attempted once more during the supplementary week.
    12. Consultations Information given at the course's website.
    13. References, textbooks and resources Course material (lecture notes) is available in electronic format. Each lecture has separate references
    14. Required learning hours and assignment

    Lectures

    28

    Preparation for lectures

    12

    Preparation for classroom test

    20

    Sum

    60
    15. Syllabus prepared by Dr. Balázs Pejó, Assistant professor
    Dr. Gergely Ács, Associate professor
    Dr. Levente Buttyán, Professor
    Department of Networked Systems and Services