News

Next PINE Meeting and Presentations

Written on 14.05.26 by Thorsten Eisenhofer

Dear Students,

Congratulations on your fantastic efforts so far! As this wave comes to a close, we would like to remind you about our next meeting on Wednesday, 20.05 at 14:15 in room C0.01.

For this meeting, we would ideally like 4-5 students to present their solutions to one of the challenges.… Read more

Dear Students,

Congratulations on your fantastic efforts so far! As this wave comes to a close, we would like to remind you about our next meeting on Wednesday, 20.05 at 14:15 in room C0.01.

For this meeting, we would ideally like 4-5 students to present their solutions to one of the challenges. If you are interested in sharing your work, please register here:
https://terminplaner6.dfn.de/b/84f32bd35213948e5b05370e6f01cdd7-1716116

Please note that, by the end of the semester, each student is expected to have given one presentation, as this is part of your final grade.

As a reminder, your presentations should be about 10 minutes and self-contained. This means that you should:
- Briefly explain the problem the challenge addresses
- Explain how your method work
- Describe what alternatives or iterations you tried
- Present some of results how your solution performs

Happy hacking,
The PINE Team

Friendly Reminder: LSF Registration Deadline

Written on 11.05.26 by Thorsten Eisenhofer

Dear Students,

just a quick reminder that the LSF registration deadline is approaching quickly. Please make sure to register by May 13 if you would like to participate in the course.

If you no longer plan to participate, we would appreciate a short email so we can keep track of the… Read more

Dear Students,

just a quick reminder that the LSF registration deadline is approaching quickly. Please make sure to register by May 13 if you would like to participate in the course.

If you no longer plan to participate, we would appreciate a short email so we can keep track of the numbers.

Happy hacking,
The PINE Team

Connecting from the university network

Written on 06.05.26 by Thorsten Eisenhofer

Dear Students,

Some of you ran into issues connecting to the servers from the university network. We checked this with our IT and found a routing issue that was likely causing the problem. It should now be fixed.

Happy hacking,
The PINE Team

P.S. Congrats to all the teams that made it into… Read more

Dear Students,

Some of you ran into issues connecting to the servers from the university network. We checked this with our IT and found a routing issue that was likely causing the problem. It should now be fixed.

Happy hacking,
The PINE Team

P.S. Congrats to all the teams that made it into the global top 5 ranking at raid-international.org ! 📈

Report template

Written on 01.05.26 by Thorsten Eisenhofer

Dear Students,

The report template is now available at:
https://cms.cispa.saarland/pine26/materials/

If you have any questions about the report or are facing problems connecting to the challenges, please reach out to us.

Happy hacking,
The PINE Team

LSF Registration

Written on 29.04.26 by Thorsten Eisenhofer

Dear Students,

LSF registration is now open. If you would like to participate in the course, please make sure to register by May 13.

The course is listed as:
12221 Research Problems in Machine Learning and Security - Seminar

Best regards,
The PINE Team

First Wave

Written on 24.04.26 by Thorsten Eisenhofer

Dear Students,

The wait is over: the first wave of challenges is live, and you can already connect to the first two challenges of the semester:
- ssh snicket@pine
- ssh cheetah@pine

Now is the perfect time to get started, explore the challenges, and claim your first points.

If you run into… Read more

Dear Students,

The wait is over: the first wave of challenges is live, and you can already connect to the first two challenges of the semester:
- ssh snicket@pine
- ssh cheetah@pine

Now is the perfect time to get started, explore the challenges, and claim your first points.

If you run into any connection issues, please let us know - we'll do our best to help you get up and running quickly. We are aware of one issue that sometimes connections from within the university network may fail. We are currently looking into this to see if this can be fixed. In the meantime, using a VPN while on campus should solve the problem.

Once you submit your first solution, you'll appear on the scoreboard at pine-aisec.org, as well as on the shared scoreboard with our friends in Vienna, Berlin, and Hamburg at raid-international.org.

Remember: points are awarded continuously, so getting started early gives you more time to climb the scoreboard!

Good luck, have fun, and happy hacking!  
The PINE Team

Show all

  PINE: Research Problems in
  Machine Learning and Security

Overview

This seminar looks at current research problems at the intersection of machine learning and computer security. Students work in small teams on hands-on challenges, gaining experience with research methods and learning how to identify and apply relevant ideas from the literature. Over the course of the semester, students will tackle six challenges covering attacks and defenses against machine learning systems, as well as the use of learning-based techniques for practical computer security tasks.

Instructor Thorsten Eisenhofer (email)
Registration Central Assignment System
No. of students     8–12

Location

E 9.1 (CISPA building) – 0.01
Schedule     Kick-off & Wave 1: Wednesday, 22.04.26, 14:00–16:00
  Wave 2: Wednesday, 20.05.26, 14:00–16:00
  Wave 3: Thursday, 18.06.26, 14:00–16:00
  Wrap-up: Wednesday, 15.07.26, 14:00–16:00
The course emphasizes experimental work on open-ended research problems, active exploration of relevant research literature, and clear communication of results. While most of this work can be carried out independently in small teams, the seminar meetings provide an important space for discussion, feedback, and learning how to present research ideas. Attendance is therefore mandatory, and active participation is expected.

Recommended Background

A strong background in machine learning and computer security is recommended. The course involves independent study, and students should be prepared to fill gaps in their prior knowledge as needed. Since much of the work is carried out remotely on a shared server, students should also have prior experience with, or be willing to independently learn, the necessary tools and workflows for remote development.

Organization

The course is organized around six challenges distributed over three waves. In each wave, students work in small teams for four to six weeks on two challenges: one focused on applying machine learning to security problems and one examining the security of machine learning systems. Challenges are run in a Kaggle-style competition format with a shared scoreboard, allowing teams to compare results throughout each wave. Students are given access to a remote server that provides the research problem and the necessary compute, and are expected to independently research relevant background, explore existing methods, experiment with different approaches, and develop and evaluate their own solutions.

Example challenge scoreboard

Grading & Deliverables

Grades are based on the results achieved in the challenges and on the clarity with which results are documented and communicated. Challenges are solved in teams, with reports reflecting the team's work, while presentations are completed individually. There are two main deliverables:

  • Technical reports. For each challenge, teams submit a short technical report (2 pages) written in the style of a mini research paper. The report briefly introduces the problem, describes the methodology, presents experimental results, and critical reflection. A report template will be provided and must be used. Technical reports and challenge results together account for 80% of the final grade.
  • Presentations. Each student gives a 10-minute presentation on one selected challenge, based on the corresponding technical report. Presentations account for the remaining 20% of the final grade.
These deliverables are intended to assess your own ability to communicate complex ideas clearly and rigorously. For this reason, the use of LLMs or other generative AI tools for drafting, editing, or preparing reports and presentations is strictly prohibited. Any use of such tools will result in a failing grade for the respective deliverable.
Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators.