Sabine Rieder

Sabine Rieder
Office: 03.11.39
ORCID: 0009-0006-6397-3100
Institut für Informatik (I7)
Technische Universität München
Boltzmannstr. 3
D-85748 Garching bei München / Germany

Since 2021, I have been doing a joint PhD with the Technical University of Munich and Audi AG.
My research interests revolve around the safety of Neural Networks, mostly abstraction and runtime monitoring.

Research Areas

Safety of Neural Network

Safety of Neural Network

We abstract neural networks to improve verification speed.

Read more »




We create a tool (Monitizer) that optimizes monitors on a NN for a specific task.

Read more »


Guessing Winning Policies in LTL Synthesis by Semantic Learning  
Jan Křetìnskỳ, Tobias Meggendorfer, Maximilian Prokop, Sabine Rieder
CAV 2023
Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks  
Vahid Hashemi, Jan Křetìnskỳ, Sabine Rieder, Jessica Schmidt
FM 2023

Student Projects

Open Projects

Evaluation of State-of-The-Art Runtime Monitoring Techniques
(Type: BT)
In this project, we want to compare different runtime monitoring techniques. We want to evaluate them on several types of unseen data and datasets to investigate the performance and capabilities of the techniques. Experiments will be carried out with the help of Monitizer.
Decision Trees for Monitoring Neural Networks
(Type: BT)
We want to explore the possibilities of using Decision Trees as a more understandable monitor for Neural Networks, potentially in combination with other monitors.

Ongoing Projects

Yifei Xu:  A Framework for Evaluation of Runtime Monitors for Object Detection Neural Networks
(Type: MT)
While Object Detection Neural Networks are of high practical relevance, there is no standard way to evaluate them yet. In addition, not many monitors for this type of NN are known. In this thesis, we develop a framework to evaluate such monitors and present basic network monitoring methods.

Finished Projects