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

Machine Learning and Security - Advanced ProjectModule description #41220 / Version 2

← Module page Deutsche Fassung
Module / Version#41220 / #2
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 instructionEnglish

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

On completion of the project, the students will have in-depth knowledge in the field of machine learning and compute security. This knowledge includes both practical and theoretical aspects of the problems covered. The students will be able to either (i) apply learning algorithms to advanced security problems/systems or (ii) apply security principles to machine learning problems/systems. In both cases, this application includes a theory-based analysis of the problem/system, a comparison of possible approaches, and the design, implementation and evaluation of the chosen solution for practical application. Moreover, the students will also reflect on the ethical and social aspects of this solution.

Content

Advanced projects are always tailored to the students' requirements and are offered as part of current research. Possible topics for the first research area (i) are learning-based approaches to detecting vulnerabilities, malicious code and privacy leaks. Possible topics for the second area (ii) are the development of attacks and defenses for learning-based and data-driven systems. In particular, practically and/or theoretically challenging problems are addressed in this module.

Module components

Compulsory area

The following courses are mandatory for this module:

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

Workload and credit points

Machine Learning and Security - Advanced (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 an advanced project. Students work individually or in groups depending on the task.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

- An ideal prerequisite is the successful completion of the module “Machine Learning and Security - Project”
- Depending on the project, in-depth knowledge of computer security and/or machine learning is strongly recommended.
- Depending on the project, the lectures “Machine Learning for Computer Security” and “Adversarial Machine Learning” provide good theoretical preparation.
- Depending on the project, the practical courses “Applied Security Lab” and “Smart Security Lab” provide good practical 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 asseessment) Project results50flexibel200h (see Test description)
(Deliverable assessment) Documentation25written20-35 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 › Kognitive Systeme / Cognitive Systems
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