Felix Morsbach

M. Sc. Felix Morsbach

About the Scientist

Felix Morsbach is a Ph.D. student at the chair of Privacy and Security at KIT. He has a background in software engineering, embedded systems, and high-performance computing. His current research interests include the privacy of behavioral data, privacy attacks on such data types, and their anonymization. He focuses on machine learning-based methods.

Research interests:

  • Privacy of Behavioral Data
  • Privacy Attacks
  • Anonymizations
  • Privacy-Preserving Machine Learning
  • Membership Inference Attacks
  • Technical Privacy Notions

If you are a KIT student interested in writing your bachelor's or master's thesis on one of the above topics, please feel free to contact me. I am always looking for motivated students.

Supervised theses

Title Qualification Graduation year
Evaluation von Privacy Threat Modeling Frameworks am Fall der elektronischen Patientenakte Master 2026
Evaluating Privacy Threats of Synthetic Click Traces via Membership Inference Attacks Master 2026
The Privacy-Utility Trade-Off of Synthetic Click Trace Generation Master 2025
Evaluating De-Identification of Sleep Data to Integrate Machine Learning into a Data Trustee Master 2024
BFId: Identity Inference Attacks utilizing Beamforming Feedback Information Master 2024
Streamlining Membership Inference Attack Research by Reusing Shadow Models Bachlor 2024
De-Identification of Health Data in a Data Trustee for Sleep Research Bachlor 2024
Influence of Convolutional Neural Network Architectures on Membership Inference Attacks Master 2023
Inferring Personal Attributes with a Mmwave Radar Master 2023
Privacy Benefits of Depth Cameras? Synthesizing RGB Images from Depth Maps Bachlor 2023
Evaluation of Countermeasures to Machine Learning Model Extraction Master 2022
Comparision of Existing Security Ontologies for Use in a Security Assistant Bachlor 2022
Charakterisierung von Privileged Access Management-Funktionen Bachlor 2021

Publications


BFId: Identity Inference Attacks Utilizing Beamforming Feedback Information
Todt, J.; Morsbach, F.; Strufe, T.
2025. Proceedings of 32nd ACM SIGSAC Conference on Computer and Communications Security (CCS ’25), Taipei, October 13–17, 2025, Association for Computing Machinery (ACM). doi:10.1145/3719027.3765062
PETs and AI: Privacy Washing and the Need for a PETs Evaluation Framework (Dagstuhl Seminar 25112)
Cristofaro, E. De; Shrishak, K.; Strufe, T.; Troncoso, C.; Morsbach, F.
2025. Dagstuhl Reports, 15 (3), 77–93. doi:10.4230/DagRep.15.3.77
Practitioner Motives to Use Different Hyperparameter Optimization Methods
Kannengiesser, N.; Hasebrook, N.; Morsbach, F.; Zöller, M.-A.; Franke, J. K. H.; Lindauer, M.; Hutter, F.; Sunyaev, A.
2025. ACM Transactions on Computer-Human Interaction. doi:10.1145/3745771
R+R: Understanding Hyperparameter Effects in DP-SGD
Morsbach, F.; Reubold, J. L.; Strufe, T.
2024. 40th Annual Computer Security Applications Conference (ACSAC), Honolulu, HI, USA, 09-13 December 2024, 1217–1230, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ACSAC63791.2024.00097
Human-Centered Design for Data-Sparse Tailored Privacy Information Provision
Goram, M.; Dehling, T.; Morsbach, F.; Sunyaev, A.
2023. Human Factors in Privacy Research. Ed.: N. Gerber, 283–298, Springer International Publishing. doi:10.1007/978-3-031-28643-8_14
Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
Morsbach, F.; Dehling, T.; Sunyaev, A.
2021. Presented at NeurIPS 2021 Workshop on Privacy in Machine Learning (PriML 2021), 14.12.2021. doi:10.48550/arXiv.2111.14924
DecFL: An Ubiquitous Decentralized Model Training Protocol and Framework Empowered by Blockchain
Morsbach, F.; Toor, S.
2021. BSCI ’21: Proceedings of the 3rd ACM International Symposium on Blockchain and Secure Critical Infrastructure, 61–68, Association for Computing Machinery (ACM). doi:10.1145/3457337.3457842