Trustworthy Machine Learning

Semester: Summer 2026

Added: May 16, 2026

Summer 2026

Instructors: Adam Dziedzic and Franziska Boenisch

Contact: adam.dziedzic@cispa.de, franziska.boenisch@cispa.de

Lectures: Wednesday 16:00-18:00, CISPA Building C0, Lecture Hall Ground Floor (Room 0.05)

Exercise Sessions: See schedule for specific tutorial and theoretical exercise slots. Course catalog: ——

CMS

Description

The deployment of machine learning applications in real-world systems necessitates methods to ensure their trustworthiness. This course explores the different aspects of trustworthy machine learning, including Privacy, Collaborative Learning, Model Confidentiality, Robustness, Fairness and Bias, Explainability, Security, and Governance.

The objective of this tutorial is to provide attendees with a comprehensive understanding of trustworthy machine learning, covering key aspects such as privacy, robustness, fairness, explainability, security, and governance. Participants will benefit by gaining practical skills in identifying and mitigating risks associated with machine learning models, including privacy attacks, model theft, bias, and adversarial threats. By the end of the course, attendees are expected to have enhanced their knowledge of cutting-edge defense strategies, developed practical skills in securing machine learning systems, and deepened their understanding of the ethical and societal implications of deploying these models in real-world scenarios.

Assignments

The course entails 4 practical graded assignments based on implementing the concepts studied during the lecture. Assignments need to be handed in groups of two.

Please submit the assignments over CMS in a ZIP file containing only the code and README+Report. Models and other artifacts should not be uploaded.

  • Assignment 1: Membership Inference – due Wednesday, May 6 at 23:59
  • Assignment 2: Stolen Model Detection – due Tuesday, May 26 at 23:59
  • Assignment 3: Robustness – due Wednesday, Jun 17 at 23:59
  • Assignment 4: Fairness – due Wednesday, Jul 8 at 23:59

Schedule

Date Topic
We, Apr 8 Overview on the Course, Administration, Intro, and Questions about Privacy I
We, Apr 15 Questions on Privacy II
We, Apr 22 Tutorial on Assignment 1, Coding in Python, Submitting your Solutions to our API
We, Apr 29 Tutorial on Theoretical Exercises for the Topic Block Privacy
We, May 6 Questions on Model stealing and defenses, both SL and SSL
We, May 13 Questions on Model Stealing and Defenses (Continue) and Tutorial on Assignment 2
We, May 20 Questions on Robustness and Tutorial on Theoretical Exercises for the Topic Block Model Stealing
We, Jun 3 Midterm-Exam (4:00 PM - 5:00 PM)
We, Jun 10 Adversarial Machine Learning / Robustness
We, Jun 17 Collaborative learning (17.6.a, 17.6.b)
We, Jun 24 Fairness and bias
We, Jul 1 Explainability (Location: HS I in E 2.5)
We, Jul 8 Security and Governance / Summary & Open Questions
We, Jul 29 Final Exam (16:00 - 18:00, Location: HS I in E 2.5)

Feedback

You can ask your questions in the respective thread in the Forum on CMS. Questions regarding the course content will be answered in the in-person lecture hours.

Course Staff