Machine Learning for Computer Security

Overview

SemesterWinter 2022
Course typeLecture + Exercises (NEW THIS YEAR!)
LecturerJun.-Prof. Dr. Wressnegger
AudienceInformatik Master & Bachelor
Credits3+2 ECTS
Time11:30–13:00
Room-101 (50.34)
LanguageEnglish
LinkTBA
RegistrationTBA

Award Winning Lecture

The lecture "Machine Learning for Computer Security" has been awarded as the "Beste Wahlvorlesung" at the KIT-Department of Informatics in the summer semester 2021.

Description

The lecture is about combining the fields of machine learning and computer security in practice. Many tasks in the computer security landscape are based on manual labor, such as searching for vulnerabilities or analyzing malware. Here, machine learning can be used to establish a higher degree of automation, providing more "intelligent" security solutions. However, also systems based on machine learning can be attacked and need to be secured.

The module introduces students to theoretic and practical aspects of machine learning in computer security. We cover basics on features, feature engineering, and feature spaces in the security domain, discuss the application of clustering and anomaly detection for malware analysis and intrusion detection, as well as, the discovery of vulnerabilities using machine learning. Additionally, we discuss the interpretability and robustness of learning-based systems.

Mode of Operation

This year we are going to do this in a flipped class-room setting. The lecture contents are distributed via video recordings, in a way that you can learn at your own speed. Additionally, we are meeting up for discussions, Q&A, and exercises in person here at the university. This way, we hopefully get the best from both worlds.

Schedule

DateTopicSlidesRecordings
02. NovIntroduction
09. NovMachine Learning 101
16. NovFrom Data to Features
23. NovEfficient String Processing
30. NovNo Lecture
07. DecAnomaly Detection for Intrusion Detection
14. DecMalware Classification
21. DecEvaluating Learning-based Systems
11. JanLearning Vulnerable Code Patterns
18. JanLearning-based Fuzzing
25. JanExplainable Machine Learning
1. FebAdversarial Machine Learning
8. FebSummary and Outlook
22. FebWritten Exam

Mailing List

News about the lecture, potential updates of the schedule, and additional material are distributed using a separate mailing list. Moreover, the list enables students to discuss topics of the lecture.

You can subscribe here.