194.055 Security, Privacy and Explainability in Machine Learning
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2022S, VU, 2.0h, 3.0EC
Lecture TubeTUWEL

Properties

  • Semester hours: 2.0
  • Credits: 3.0
  • Type: VU Lecture and Exercise
  • LectureTube course
  • Format: Presence

Learning outcomes

After successful completion of the course, students are able to...

- Identify threats to privacy of individuals in machine learning datasets

- Select fitting solutions for privacy-preserving machine learning

- Understand attack vectors on machine learning models, and how attacls can be detected and mitigated

- Select fitting concepts for explainable and interpretable machine learning

Subject of course

  • Privacy-preserving techniques to anonymize sensitive information in the input data, e.g. to facilitate data sharing, with a specific focus on the implications on the utility of the data and the models trained thereon. This includes e.g. k-anonymity and related models such as l-diversity, as well as differential privacy, etc.
  • Privacy-preserving techniques, such as differential privacy, to prevent information leaks from trained models
  • Attack vectors on machine learning models, e.g. membership attacks, and model stealing, Adversary Input Generation and how to limit them
  • Backdoor embedding to manipulate the behaviour of seemingly benign models for malicious purposes
  • Privacy-preserving computation of machine learning models, e.g. with secure multi-party computation, and homomorphic encryption approaches
  • Explainability of machine learning models to facilitate a better understanding and trust in the models, e.g. via visualization, rule extraction, Zero-Shot Learning

 

Teaching methods

The course consists of lectures and exercises. Lectures will be held in-class.  Exercises include the application of privacy-preserving, secure and explainabel machine learning techniques for various data sets and implementation of thses techniques. The exercises are prepared at home and will be presented/discussed during the exercise classes.  

Mode of examination

Immanent

Additional information

The SPEML Lecture will be held in class!


Preliminary talk (Vorbesprechung) & Intro: 03.03.2022, 11:30, EI 10

 

 

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Thu11:00 - 13:0003.03.2022 - 07.04.2022EI 10 Fritz Paschke HS - UIW Lecture
Thu11:00 - 13:0028.04.2022 - 30.06.2022FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu11:00 - 13:0005.05.2022FAV Hörsaal 2 Lecture
Security, Privacy and Explainability in Machine Learning - Single appointments
DayDateTimeLocationDescription
Thu03.03.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu10.03.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu17.03.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu24.03.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu31.03.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu07.04.202211:00 - 13:00EI 10 Fritz Paschke HS - UIW Lecture
Thu28.04.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu05.05.202211:00 - 13:00FAV Hörsaal 2 Lecture
Thu05.05.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu12.05.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu19.05.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu02.06.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu23.06.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture
Thu30.06.202211:00 - 13:00FAV Hörsaal 3 Zemanek (Seminarraum Zemanek) Lecture

Examination modalities

- Solving of exercises regarding experiments in secruity, privacy and explainability of machine learning, using a software toolkit of the student's choice (e.g. Python scikit-learn, Matlab, R, WEKA, ...)

- Written exam (closed book) - most likely in-class, but via TUWEL. In case of low enrollment, the exam can also be conducted orally (also, depending on the development of the pandemic situation, most likely on-line).

Exams

DayTimeDateRoomMode of examinationApplication timeApplication modeExam
Mon12:00 - 14:0017.10.2022EI 10 Fritz Paschke HS - UIW written19.09.2022 00:00 - 14.10.2022 23:59TISSExam (re-take)

Course registration

Begin End Deregistration end
27.01.2022 00:00 06.04.2022 23:59 06.04.2022 23:59

Curricula

Literature

No lecture notes are available.

Previous knowledge

184.702 Machine Learning, or a similar Machine Learning lecture

Preceding courses

Language

English