Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Machine Learning and Security - ProjectModule description #41102 / Version 4

← Module page Deutsche Fassung
Module / Version#41102 / #4
ValiditySince Winter semester 2026/27
Available language(s)English, German
Credit points9
Person responsible for the moduleRieck, Konrad
GradingGraded
Exam formatPortfolio examination
Language(s) of instructionGerman

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34353000 FG Maschinelles Lernen und IT-Sicherheit

Contact

OfficeNot specified
Contact personRieck, Konrad
E-mail addressrieck@tu-berlin.de
Websitehttps://mlsec.tu-berlin.de

Learning outcomes

After completion of the course, students have a thorough understanding of the intersection of machine learning and security. They are able to either (i) apply learning algorithms to advanced problems/systems in security or (ii) apply principles of security to advanced problems/systems in machine learning. Moreover, they are capable of designing, developing, and evaluating corresponding solutions.

Content

Projects will always be customized regarding the students‘ requirements, and offered within the scope of current research. Possible topics for the first branch (i) include learning-based approaches for detecting vulnerabilities, malicious code, and privacy leaks. Possible topics for the second branch (ii) include the development of attacks and defenses for learning-based and data-driven systems.

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Machine Learning and Security ProjectProject Winter and summer semester[en]6 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (2)

Machine Learning and Security Project (Project) 2

All groups of this course in the catalog

Workload and credit points

Machine Learning and Security Project (Project)

Workload descriptionMultiplierHoursTotal
Project work1200 h200 h
Writing of report120 h20 h
Background research120 h20 h
Meetings with advisors52 h10 h
Preparation of talk120 h20 h
270 h

The workload of the module adds up to 270 hours. The module therefore comprises 9 credit points.

Description of teaching and learning methods

The module consists of a project. Students work individually or in groups depending on the task.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

- Depending on the particular project, knowledge of computer security and/or machine learning is recommended.
- Depending on the particular project, the lectures "Machine Learning for Computer Security" and "Adversarial Machine Learning" provide a good preparation.

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatPortfolio examination
Type of portfolio examination100 points in total
LanguageEnglish, German

Test elements

NamePoints/WeightCategoryDuration/Extent
(Deliverable assessment) Project results50flexibel200h (see Test description)
(Deliverable assessment) Documentation25written10-25 pages
(Deliverable assessment) Presentation25oral30 minutes

Exam description

The grade for the portfolio examination is determined based on the project results, the documentation, and the presentation. The project results may include, depending on the topic, developed software, an IT system, and/or conducted experiments. The scope corresponds to a workload of approximately 200 hours. The size of the source code, such as the number of lines, is not considered in the evaluation, as it is not indicative of quality. Instead, the following aspects are assessed: (1) functionality, i.e., correctness and completeness of the implementation; (2) methodology, i.e., the suitability of the chosen methods and tools; (3) reproducibility of the results, including documentation and testability; and (4) code quality, project structure, and adherence to common conventions.

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Winter and summer semester.

Maximum number of participants

The maximum capacity of participants is 10.

Registration procedures

Registration for the work placement is handled via the ISIS learning platform. Participants in the project are usually selected during the first week of the semester.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

No recommended literature given

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Computer Engineering
Computer Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks
Computer Science (Informatik)
Computer Science (Informatik) (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiet › Verteilte Systeme und Netze / Distributed Systems and Networks
Electrical Engineering
Electrical Engineering (M. Sc.) - StuPO 2015
WS 2026/27Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering
Industrial Engineering and Management
Industrial Engineering and Management (M. Sc.) - StuPO 2026
WS 2026/27Engineering Sciences / Specialization › AI Engineering › Data and Software Engineering
Information Systems Management (Wirtschaftsinformatik)
Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017
WS 2026/27Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks

Miscellaneous

Not specified