| Integration of module into courses of studies: |
Informatik, B.Sc., FSPO 2021 Schwerpunkt Informatik,
Medieninformatik, B.Sc., FSPO 2021 Schwerpunkt Medieninformatik,
Software Engineering, B.Sc., FSPO 2021 Schwerpunkt Software Engineering,
Informatik, M.Sc., FSPO 2021 Praktische und Angewandte Informatik,
Medieninformatik, M.Sc., FSPO 2021 Praktische und Angewandte Informatik,
Software Engineering, M.Sc., FSPO 2021 Praktische und Angewandte Informatik,
Künstliche Intelligenz, M.Sc., FSPO 2021 Praktische und Angewandte Informatik,
Informatik, B.Sc., FSPO 2022 Vertiefungsbereich,
Medieninformatik, B.Sc., FSPO 2022 Vertiefungsbereich,
Informatik, M.Sc., FSPO 2022 Praktische Informatik,
Medieninformatik, M.Sc., FSPO 2022 Praktische Informatik,
Software Engineering, M.Sc., FSPO 2022 Praktische Informatik,
Künstliche Intelligenz, M.Sc., FSPO 2022 Praktische Informatik,
Software Engineering, B.Sc., FSPO 2022 SE Wahlbereich |
| Modes of learning and teaching: |
Maschinelles Lernen & IT-Sicherheit (Vorlesung) (2 SWS),
Machine Learning & Security (Übung) (2 SWS) |
| Module authority: |
Prof. Dr. Frank Kargl |
| Lecturer: |
Prof. Dr. Frank Kargl |
| Language: |
english |
| Turn / Duration: |
every summer term / 1 |
| Requirements (contentual): |
Basic knowledge of computer networks, machine learning, and IT security as provided by foundational Bachelor courses in these fields.,Familiarity with AI-related programming and open-source tools such as Python, scitkit-learn and PyTorch. |
| Requirements (formal): |
None |
| Basis for: |
Advanced projects and B.Sc. or M.Sc. thesis in the field. |
| Learning objectives: |
Upon completing this module, students will
- understand existing threats to machine-learning as well as possible countermeasures,
- understand the application of machine-learning in security and in particular network security for tasks like security monitoring and intrusion detection,
- be able to implement robust and secure machine-learning systems,
- have developed practical skills in using ML-based tools for solving real-world problems in (network-)security,
- be able to implement and evaluate ML models for tasks such as anomaly detection, and malware identification. |
| Content: |
The module provides an in-depth exploration of the intersection of ML, and (network-)security, focusing on:
- Security of ML: Threats, risks, attack classes and mitigations.
- Application of ML in IT-Security: Using ML to detect and mitigate cyber threats for tasks like intrusion detection, malware analysis, or phishing defense.
- Case Studies: As part of the lab, students will be tasked with real-world scenarios from areas like security monitoring, anomaly, or phishing detection and challenged to innovate and enhance over existing solutions. |
| Literature: |
Lecture notes, research papers, and case study materials will be provided as part of lecture material.,Supplementing material: Clarence Chio, David Freeman, ‘Machine Learning and Security’, O’Reilly Media, Inc., ISBN: 9781491979907, https://learning.oreilly.com/library/view/machine-learning-and/9781491979891/ |
| Grading procedure: |
The module examination consists of a graded written or oral examination, depending on the number of participants. If a specified academic work is achieved, a grade bonus is awarded in accordance with §17 (3a) of the General Examination Regulations at the immediately following examination. The examination grade is improved by one grade level, but not better than 1.0. An improvement from 5.0 to 4.0 is not possible. The examination form will be announced in good time before the examination is held - at least 4 weeks before the examination date. |
| Estimation of effort: |
Contact Hours: 60 hours (Lecture and Practical Exercises)
Self-study and Assignments: 120 hours (Self-study, preparation for exercises, case studies, and exam)
Total: 180 hours |
