Privacy is a fundamental human right! And yet, technological advances (in particular in computer science) can often undermine privacy. In this class we will see how to formalize various notions of privacy and how to build systems that preserve privacy, by combining techniques from cryptography and statistics. The later parts of the course will focus on applications to machine learning.
Learning objective
By the end of the course, students will be able to: - Reason about privacy concerns and the appropriate formalizations - Combine tools from cryptography and statistics to build privacy mechanisms - Assess, evaluate and prove privacy protection of a mechanism.
Content
The first half of the class will cover topics from cryptography such as secure multiparty computation, zero-knowledge proofs, PIR, ORAM, anonymous communication, etc. The second half will cover statistical notions of privacy, in particular differential privacy, and selected topics in machine learning privacy.
Lecture notes
Lecture notes will be posted on Moodle.
Literature
Boneh & Shoup - A Graduate Course in Applied Cryptography References to relevant research papers will be provided
Prerequisites / Notice
Basic knowledge in cryptography, probability and machine learning is recommended but not required.
Performance assessment
Performance assessment information (valid until the course unit is held again)
Repetition only possible after re-enrolling for the course unit.
Additional information on mode of examination
Last cancellation/deregistration date for this graded semester performance: 7 November 2024! Please note that after that date no deregistration will be accepted and the course will be considered as "fail".
Performance assessment as a semester course