Suchergebnis: Katalogdaten im Herbstsemester 2021

Informatik Master Information
Master-Studium (Studienreglement 2020)
Vertiefungen
Vertiefung in Secure and Reliable Systems
Wahlfächer
NummerTitelTypECTSUmfangDozierende
252-1411-00LSecurity of Wireless Networks Information W6 KP2V + 1U + 2AS. Capkun, K. Kostiainen
KurzbeschreibungCore Elements: Wireless communication channel, Wireless network architectures and protocols, Attacks on wireless networks, Protection techniques.
LernzielAfter this course, the students should be able to: describe and classify security goals and attacks in wireless networks; describe security architectures of the following wireless systems and networks: 802.11, GSM/UMTS, RFID, ad hoc/sensor networks; reason about security protocols for wireless network; implement mechanisms to secure
802.11 networks.
InhaltWireless channel basics. Wireless electronic warfare: jamming and target tracking. Basic security protocols in cellular, WLAN and
multi-hop networks. Recent advances in security of multi-hop networks; RFID privacy challenges and solutions.
263-2400-00LReliable and Trustworthy Artificial Intelligence Information W6 KP2V + 2U + 1AM. Vechev
KurzbeschreibungCreating reliable and explainable probabilistic models is a fundamental challenge to solving the artificial intelligence problem. This course covers some of the latest and most exciting advances that bring us closer to constructing such models.
LernzielThe main objective of this course is to expose students to the latest and most exciting research in the area of explainable and interpretable artificial intelligence, a topic of fundamental and increasing importance. Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of problems.

To facilitate deeper understanding, an important part of the course will be a group hands-on programming project where students will build a system based on the learned material.
InhaltThis comprehensive course covers some of the latest and most important research advances (over the last 3 years) underlying the creation of safe, trustworthy, and reliable AI (more information here: https://www.sri.inf.ethz.ch/teaching/reliableai21):

* Adversarial Attacks on Deep Learning (noise-based, geometry attacks, sound attacks, physical attacks, autonomous driving, out-of-distribution)
* Defenses against attacks
* Combining gradient-based optimization with logic for encoding background knowledge
* Complete Certification of deep neural networks via automated reasoning (e.g., via numerical relaxations, mixed-integer solvers).
* Probabilistic certification of deep neural networks
* Training deep neural networks to be provably robust via automated reasoning
* Fairness (different notions of fairness, certifiably fair representation learning)
* Federated Learning (introduction, security considerations)
Voraussetzungen / BesonderesWhile not a formal requirement, the course assumes familiarity with basics of machine learning (especially linear algebra, gradient descent, and neural networks as well as basic probability theory). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH).

For solving assignments, some programming experience in Python is expected.
263-4657-00LAdvanced Encryption SchemesW5 KP2V + 1U + 1AR. Gay
KurzbeschreibungPublic-Key Encryption has had a significant impact by enabling remote parties to communicate securely via an insecure channel. Latest schemes go further by providing a fine-grained access to the encrypted data.
LernzielThe student is comfortable with formal security definitions and proof techniques used to analyze the security of the latest encryption schemes with advanced features. This prepares the student to start reading research papers on the field.
InhaltWe will start by presenting the notion of Public-Key Encryption with its various security guarantees and some constructions. Then we will look into encryption schemes with fine-grained access control to the encrypted data, such as identity-based encryption or attribute-based encryption and present different methodology to prove their security.
LiteraturLinks to relevant research papers will be given in the course materials.
Voraussetzungen / BesonderesIt is recommended for students to have prior exposure to cryptography, e.g.the D-INFK course "Digital Signatures" or "Applied Cryptography".
263-4665-00LZero-Knowledge Proofs Belegung eingeschränkt - Details anzeigen
Number of participants limited to 50.
W5 KP2V + 1U + 1AJ. Bootle
KurzbeschreibungThis course is a detailed introduction to zero-knowledge proof protocols.
LernzielTo understand various methods of constructing zero-knowledge proof protocols, and be able to analyse their security properties.
InhaltThe course will discuss interactive zero-knowledge proofs based on various commitment schemes, and explore connections to other areas like secure multi-party computation. The course may also describe some more advanced constructions of non-interactive proofs.
SkriptThe course notes will be written in English.
Voraussetzungen / BesonderesStudents should have taken a first course in Cryptography (as taught in the Information Security course at Bachelor’s level). Confidence with algebra and probability is desirable.
227-0579-00LHardware SecurityW7 KP2V + 2U + 2AK. Razavi
KurzbeschreibungThis course covers the security of commodity computer hardware (e.g., CPU, DRAM, etc.) with a special focus on cutting-edge hands-on research. The aim of the course is familiarizing the students with hardware security and more specifically microarchitectural and circuit-level attacks and defenses through lectures, reviewing and discussing papers, and executing some of these advanced attacks.
LernzielBy the end of the course, the students will be familiar with the state of the art in commodity computer hardware attacks and defenses. More specifically, the students will learn about:

- security problems of commodity hardware that we use everyday and how you can defend against them.
- relevant computer architecture and operating system aspects of these issues.
- hands-on techniques for performing hardware attacks.
- writing critical reviews and constructive discussions with peers on this topic.

This is the course where you get credit points by building some of the most advanced exploits on the planet! The luckiest team will collect a Best Demo Award at the end of the course.
LiteraturSlides, relevant literature and manuals will be made available during the course.
Voraussetzungen / BesonderesKnowledge of systems programming and computer architecture is a plus.
  •  Seite  1  von  1