263-2400-00L  Reliable and Trustworthy Artificial Intelligence

SemesterAutumn Semester 2023
LecturersM. Vechev
Periodicityyearly recurring course
Language of instructionEnglish



Courses

NumberTitleHoursLecturers
263-2400-00 VReliable and Trustworthy Artificial Intelligence2 hrs
Wed14:15-16:00HG G 3 »
M. Vechev
263-2400-00 UReliable and Trustworthy Artificial Intelligence
Exercise session will start in the second week of the semester.
2 hrs
Mon12:15-14:00CAB G 56 »
Wed12:15-14:00CAB G 51 »
30.10.12:15-14:00HG G 3 »
M. Vechev
263-2400-00 AReliable and Trustworthy Artificial Intelligence1 hrsM. Vechev

Catalogue data

AbstractCreating reliable, secure, robust, and fair machine learning models is a core challenge in artificial intelligence and one of fundamental importance. The goal of the course is to teach both the mathematical foundations of this new and emerging area as well as to introduce students to the latest and most exciting research in the space.
ObjectiveUpon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of engineering and research problems. To facilitate deeper understanding, the course includes a group coding project where students will build a system based on the learned material.
ContentThe course is split into 4 parts:

Robustness of Machine Learning
--------------------------------------------

- Adversarial attacks and defenses on deep learning models.
- Automated certification of deep learning models (major trends: convex relaxations, branch-and-bound, randomized smoothing).
- Certified training of deep neural networks (combining symbolic and continuous methods).

Privacy of Machine Learning
--------------------------------------

- Threat models (e.g., stealing data, poisoning, membership inference, etc.).
- Attacking federated machine learning (across vision, natural language and tabular data).
- Differential privacy for defending machine learning.
- AI Regulations and checking model compliance.

Fairness of Machine Learning
---------------------------------------

- Introduction to fairness (motivation, definitions).
- Enforcing individual fairness (for both vision and tabular data).
- Enforcing group fairness (e.g., demographic parity, equalized odds).

Robustness, Privacy and Fairness of Foundation Models
---------------------------------------------------------------------------

- We discuss all previous topics, as well as programmability, in the context of latest foundation models (e.g., LLMs).

More information here: Link.
Prerequisites / NoticeWhile 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).


The coding project will utilize Python and PyTorch. Thus some programming experience in Python is expected. Students without prior knowledge of PyTorch are expected to acquire it early in the course by solving exercise sheets.
CompetenciesCompetencies
Subject-specific CompetenciesConcepts and Theoriesassessed
Techniques and Technologiesassessed
Method-specific CompetenciesAnalytical Competenciesassessed
Problem-solvingassessed
Personal CompetenciesCreative Thinkingassessed
Critical Thinkingassessed

Performance assessment

Performance assessment information (valid until the course unit is held again)
Performance assessment as a semester course
ECTS credits6 credits
ExaminersM. Vechev
Typesession examination
Language of examinationEnglish
RepetitionThe performance assessment is only offered in the session after the course unit. Repetition only possible after re-enrolling.
Mode of examinationwritten 120 minutes
Additional information on mode of examination30% of your grade is determined by mandatory project work and 70% is determined by a written exam.

Students who are repeating the course are required to repeat the project work.
Written aidsTwo A4-pages (i.e. one two-sided or two one-sided A4-sheets of paper), either handwritten or 11 point minimum font size.
This information can be updated until the beginning of the semester; information on the examination timetable is binding.

Learning materials

 
Main linkInformation
Only public learning materials are listed.

Groups

No information on groups available.

Restrictions

There are no additional restrictions for the registration.

Offered in

ProgrammeSectionType
CAS in Computer ScienceFocus Courses and ElectivesWInformation
Cyber Security MasterElective CoursesWInformation
DAS in Data ScienceMachine Learning and Artificial IntelligenceWInformation
Data Science MasterSubject-Specific ElectivesWInformation
Data Science MasterCore ElectivesWInformation
Computer Science MasterElective CoursesWInformation
Computer Science MasterElective CoursesWInformation
Computer Science MasterMinor in Machine LearningWInformation
Computer Science MasterMinor in Programming Languages and Software EngineeringWInformation
Computational Science and Engineering MasterElectivesWInformation
Science, Technology, and Policy MasterData and Computer ScienceWInformation
Statistics MasterSubject Specific ElectivesWInformation