Please come by at my office, or contact me via email.


Please encrypt emails addressed to me.

S/MIME certificate: download

PGP key: download

PGP fingerprint: FC02 6F24 803C F944 5CE1  32C9 E246 00E0 BC0F 483D.

Matthias Matousek

I have been studying Computer Sciene in Media at the University of Ulm until the summer of 2015. I also spent one year of my studies (2013-2014) in the Netherlands where I visited lectures at three different universities: University of Twente, Eindhoven University of Technology, and Radboud Unversity Nijmegen. The lectures were part of the Kerckhoffs Institute for Computer Security. For my Master's Thesis I was working on a secure processor called Secure Execution PUF-based Processor (SEPP). In summer 2015 I joined the Institute of Distributed Systems, where I am now working as a research assistant.


I am generally interested in security and privacy of IT systems. Specifically, I am working on the privacy of interconnected vehicles. Furthermore, I am interested in enabling private communication (such as cryptography in messenger services) in a user-friendly way.





I gladly supervise bachelor's, master's and diploma theses that fit into my research interests. My currently available topics for thesis and projects are listed below. Ongoing and completed thesis can be viewed here.

Available Thesis Topics

Matousek, Matthias
Machine Learning with TensorFlow Privacy
Master's thesis, Bachelor's thesis, Project
Institute of Distributed Systems,
in preparation

Abstract: Machine learning offers great opportunities, but also comes with risks. Especially the privacy risks are becoming more prevalent in the discussions about machine learning. Recently, Google published a machine learning library called TensorFlow Privacy. Its goal is to make it easier for developers and researchers to build privacy-preserving machine learning models. Specifically, it utilizes Differential Privacy, which mathematically guarantees that the training data to create the models is protected from being extracted. The goal of this thesis or project is to become familiar with the TensorFlow Privacy library, to understand and be able to explain the techniques which are implemented in it, to be able to build privacy-preserved machine learning models, and possibly to implement own protection techniques that could enhance the TensorFlow Privacy library.



Kleber, Stephan; Unterstein, Florian; Hiller, Matthias; Slomka, Frank; Matousek, Matthias; Kargl, Frank; Bösch, Christoph
Secure Code Execution: A Generic PUF-driven System Architecture
21st Information Security Conference
October 2018
Matousek, Matthias; Bösch, Christoph; Kargl, Frank
Poster: Privacy-Preserving Decision Trees
Privacy in Machine Learning and Artificial Intelligence Workshop at ICML 2018
July 2018
Matousek, Matthias; Yassin, Mahmoud; Al-Momani, Ala'a; van der Heijden, Rens W.; Kargl, Frank
Robust Detection of Anomalous Driving Behavior
IEEE 87th Vehicular Technology Conference (VTC)
June 2018


Berlin, Olga; Held, Albert; Matousek, Matthias; Kargl, Frank
POSTER: Anomaly-Based Misbehaviour Detection in Connected Car Backends
2016 IEEE Vehicular Networking Conference (VNC)
October 2016
Matousek, Matthias; Bösch, Christoph; Kargl, Frank
Using Searchable Encryption to Protect Privacy in Connected Cars
Proceedings of the 4th GI/ITG KuVS Fachgespräch Inter-Vehicle Communication


Kleber, Stephan; Unterstein, Florian; Matousek, Matthias; Kargl, Frank; Slomka, Frank; Hiller, Matthias
Design of the Secure Execution PUF-based Processor (SEPP)
Workshop on Trustworthy Manufacturing and Utilization of Secure Devices, TRUDEVICE 2015
September 2015
Kleber, Stephan; Unterstein, Florian; Matousek, Matthias; Kargl, Frank; Slomka, Frank; Hiller, Matthias
Secure Execution Architecture based on PUF-driven Instruction Level Code Encryption
July 2015


Nikolov, Vladimir; Matousek, Matthias; Rautenbach, Dieter; Draque Penso, Lucia; Hauck, Franz J.
ARTOS: System Model and Optimization Algorithm
Document number: VS-R08-2012
Institute of Distributed Systems, University of Ulm,
December 2012
Export as: BibTeX, XML