Registration for this course is open until Monday, 03.11.2025 23:59.

News

Currently, no news are available

Machine Learning in Cybersecurity

Registration is now open!
Please register on this site in order to get access to material and stay in touch.

 

Recent advances in Machine Learning have led to strong performance in a wide range of tasks which led to a wide spread deployement roll out of such systems. ChatGPT and CoPilots for code and office applications just being a few prominent examples. In terms of privacy and security, this is a double-edged sword. ML techniques can be used to efficiently detect and prevent attacks (e.g., intrusion detection). However, their deployment to many real-world sensitive systems (e.g., self-driving cars, the cloud) also makes them susceptible to numerous attacks. As AI and ML becomes part of our IT infrastructure, we have to know and defend against cybersecurity threats. Recent uplift studies and use of AI in Capture the Flag Challenges have shown that the impact of agentic AI on the cybersecurity landscape will be significant. We will also discuss some of these latest developments.

The course explores in-depth both of these sides to Machine Learning and Cyber Security. The content addresses the following areas:

  1. Short ML recap
  2. ML for improving security
  3. Attacks on ML
  4. Defenses for ML
  5. Security of Large Language Models
  6. AI for CTF
  7. Impact of AI on Cybersecurity

 

Logistics:

  • Lectures will be on Thursdays 8:30am to 10am

  • Location: CISPA Lecture Hall, Stuhlsatzenhaus 5

  • First lecture on October 16th

  • Tentative date for exercise/tutorial classes: Wednesdays 4:15pm to 5:45pm
  • Modalities:

    • In person
    • Zoom
    • Video recording

Prerequisits

While we do a very brief recap in the beginning, the course requires knowledge on Machine Learning!

Material

Once you have registered - you have access to the internal pages with further information / material (under construction).

Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators.