Privacy-Preserving Technologies

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

Last updated: 2019. április 3.

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. Gergely Ács assistant professor,Department of Networked Systems and Services

Dr. Levente Buttyán associate professor, Department of Networked Systems and Services

6. Pre-requisites
Ajánlott:
The course cannot be taken for students who already took VIETM294 Személyes és közadatok kezelése
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, source/binary code, machine learning models), 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 also required by the European General Data Protection Regulation (GDPR).
8. Synopsis

1. week
Introduction and Motivation

 
2. week
Legal background of Data Protection: GDPR

 
3. week
Cryptography: Homomorphic Encryption, Private Set Intersection, Secure Multiparty Computation

4. week
Privacy-preserving communication 1: TOR and attacks on TOR

 
5. week
Privacy-preserving communication 2: Secure Messaging (Signal), Oblivious Transfer, Private Information Retrieval

 
6. week
Web Tracking and Anti-Tracking


7. week
Personal data leakage from relational data: Uniqueness, Attribute Inference, Linking


8. week
Personal data leakage from unstructured data: Detection with Machine Learning, Web page fingerprinting, Code stylometry


9. week
Personal data leakage from aggregate data: Query auditing, Location recovery from density, Membership attack


10. week
Data anonymization: K-anonymity, Differential Privacy, RAPPOR

 
11. week
Privacy in Machine Learning: Modell inversion, Membership attack, Fairness

 
12. week
Interdependent Privacy


13-14. week
Psychological profiling and manipulation, Cognitive Security

9. Method of instruction Lectures
10. Assessment

a.    during the semester:
Fulfilling the requirements 1 classroom test.
The final grade is the grade obtained for the test.

b.    during the exam period: -

c.    preliminary exam: - 

11. Recaps Failed classroom tests can be retaken again on the supplement 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

16

Preparation for classroom test

16

Sum

60

15. Syllabus prepared by Dr. Ács Gergely    assistant professor    BME-HIT,
Dr. Levente Buttyán    associate professor    BME-HIT