| NUMBER: | 142221 |
| SHORT: | MPMLS |
| MODULBEAUFTRAGTE:R: | Prof. Dr. Thorsten Holz, M. Sc. Thorsten Eisenhofer, M. Sc. Joel Frank |
| LECTURER: | Prof. Dr. Thorsten Holz |
| FACULTY: | Fakultät für Informatik |
| LANGUAGE: | German |
| SWS: | 3 SWS |
| CREDITS: | see examination rules |
| WORKLOAD: | |
| OFFERED IN: | each semester |
EXAMS
| FORM: | Praktikum. studienbegleitend |
| ANMELDUNG: | Direkt bei der Dozentin bzw. dem Dozenten |
| DATE: | 0000-00-00 |
| START: | 00:00:00 |
| DURATION: | |
| ROOM: |
LERNFORM
practical course
LERNZIELE
The students obtain a profound understanding of modern machine learning techniques and their applications in the area of computer security. More specifically, the participants are proficient in corresponding ML algorithms and can analyze complex problems on their own. The students can design and implement ML algorithms on their own and learn how to perform research in the intersection of machine learning and computer security.
CONTENT
The practical course provides an introduction to various machine learning (ML) techniques and their application in computer security. In six exercises, we plan to cover the following topics:- Linear and logistic regression
- Clustering algorithms (e.g., k-nearest neighbors) and classification algorithms
- Unsupervised Learning
- Support vector machines (SVM)
- Deep Learning
- Adversarial Machine Learning
We will cover different applications of these techniques in areas such as:
- Spam classification
- Malware clustering
- Deep fake detection
The course will cover tools such as NumPy (https://numpy.org/) and PyTorch (https://pytorch.org/). We expect that students perform their own research and investigation to solve the exercises.
REQUIREMENTS CREDITS
Passed lab work
RECOMMENDED PRIOR KNOWLEDGE
Basic knowledge of Python is strongly recommended. The course Deep Learning offered by Prof. Fischer covers some recommended basics.
MISC INFORMATION
here is a mandatory meeting every two weeks during which we present the new exercises. Every other week, we offer an optional meeting to answer questions. All materials for the course are available via Moodle, please register for the course online.At most 20 students can participate in the practical course. More information on the planned schedule and the formal requirements are discussed in a meeting that takes place in the first week of the semester, please also see the Moodle course.