Machine Learning and Security - Master SeminarModule description #41104 / Version 1
- 3 CP
- Portfolio examination
- Graded
- Winter and summer semester
- German
| Module / Version | #41104 / #1 |
|---|---|
| Validity | Since Summer semester 2023 |
| Available language(s) | German |
| Credit points | 3 |
| Person responsible for the module | Rieck, Konrad |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | German |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Softwaretechnik und Theoretische Informatik |
| Academic chair | 34353000 FG Maschinelles Lernen und IT-Sicherheit |
Contact
| Office | Not specified |
|---|---|
| Contact person | Rieck, Konrad |
| E-mail address | rieck@tu-berlin.de |
| Website | https://mlsec.tu-berlin.de |
Learning outcomes
Through this course, students will acquire the skills to:
- Analyze and understand scientific literature critically
- Deliver effective scientific presentations
- Prepare clear and precise scientific reports.
Students investigate current and advanced research topics in machine learning and security. They reflect on the technical and ethical impact of security on society and policy.
- Analyze and understand scientific literature critically
- Deliver effective scientific presentations
- Prepare clear and precise scientific reports.
Students investigate current and advanced research topics in machine learning and security. They reflect on the technical and ethical impact of security on society and policy.
Content
The seminar is concerned with advanced topics in machine learning and security. This includes
- recent approaches for finding security vulnerabilities, analyzing malicious software, detecting intrusions, exploring privacy leaks and other security properties, as well as
- new attacks and defenses in machine learning, evasion and poisoning attacks, membership inference and other privacy attacks as well as completely new attacks for learning-based and data-based systems.
- recent approaches for finding security vulnerabilities, analyzing malicious software, detecting intrusions, exploring privacy leaks and other security properties, as well as
- new attacks and defenses in machine learning, evasion and poisoning attacks, membership inference and other privacy attacks as well as completely new attacks for learning-based and data-based systems.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Master Seminar: Machine Learning and Security | Seminar | Winter and summer semester | [en] | 2 | WS 2026/27 (2) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (2)
Master Seminar: Machine Learning and Security (Seminar) 2
- Master Seminar: Machine Learning and Security (Seminar) ALMO: Attacks on Large Language Models (Intro)
- Master Seminar: Machine Learning and Security (Seminar) ALMO: Attacks on Large Language Models (Presentations)
Workload and credit points
Master Seminar: Machine Learning and Security (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Writing of seminar report | 1 | 50 h | 50 h |
| Preparation of talk | 1 | 25 h | 25 h |
| Active participation | 10 | 1 h | 10 h |
| Reviews | 1 | 5 h | 5 h |
| 90 h | |||
The workload of the module adds up to 90 hours. The module therefore comprises 3 credit points.
Description of teaching and learning methods
The students have to read current and advanced research papers, prepare a talk, write a scientific report and review reports of other students. Students are also required to attend the talks of other participants. Note: Depending on scheduling circumstances, the talks may be held in block meetings near the end of the semester instead of the usual weekly rhythm. Details will be provided at the introductory meeting.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
- Good knowledge of machine learning and/or security is highly recommended.
- Depending on the seminar's topic, the lectures "Machine Learning for Computer Security" and "Adversarial Machine Learning" provide a good preparation for the course.
- Depending on the seminar's topic, the lectures "Machine Learning for Computer Security" and "Adversarial Machine Learning" provide a good preparation for the course.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English, German |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| Seminar report | 45 | written | 6-8 Seiten |
| Talk | 45 | oral | 30 Minuten |
| Reviews | 10 | written | 2-3 Seiten |
Exam description
The grade of the seminar is calculated from the seminar report (45%) and the presentation (45%). In addition, the reviews are included with 10%. The overall evaluation is based on the scientific, structural, and linguistic quality as well as the extent of the different examination elements.
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
Die Anmeldungen für das Seminar werden über die Lehrplattform ISIS abgewickelt.
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 version | Semester(s) | Curriculum component |
|---|---|---|
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks |
| WS 2025/26 | Wahlpflicht Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| SS 2026 | Wahlpflicht Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet B › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Kognitive Systeme / Cognitive Systems |
| WS 2025/26 | Studiengebiete › Data and Software Engineering / Data and Software Engineering | |
| SS 2026 | Studiengebiete › Kognitive Systeme / Cognitive Systems | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiet › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | SS 2025 | Wahlpflicht Studiengebiete Fak. IV › Verteilte Systeme und Netze / Distributed Systems and Networks |
| WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering | |
| SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering | |
| WS 2026/27 | Wahlpflichtbereich › Studiengebiete Fak. IV › Data and Software Engineering / Data and Software Engineering | |
| Industrial Engineering and Management Industrial Engineering and Management (M. Sc.) - StuPO 2026 | WS 2026/27 | Engineering Sciences / Specialization › AI Engineering › Data and Software Engineering |
| Information Systems Management (Wirtschaftsinformatik) Information Systems Management (Wirtschaftsinformatik) (M. Sc.) - StuPO 2017 | SS 2025 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks |
| WS 2025/26 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks | |
| SS 2026 | Wahlpflichtbereich › Fachstudium Informatik › Data and Software Engineering | |
| WS 2026/27 | Wahlpflichtbereich › Fachstudium Informatik › Verteilte Systeme und Netze / Distributed Systems and Networks |
Miscellaneous
Not specified