Jonas Möller
Jonas Möller
Doctoral Researcher
Affiliation: BIFOLD
I am a PhD student in the research group of Konrad Rieck at TU Berlin, working at the intersection of machine learning and security. My research focuses on the gap between theoretical security assumptions and real-world system behavior. Specifically, I investigate the impact of implementation differences of machine learning components on the security of the entire system.
Jonas Möller, Erik Imgrund, Thorsten Eisenhofer, Konrad Rieck
Hardware-Triggered Backdoors
Felix Weissberg, Lukas Pirch, Erik Imgrund, Jonas Möller, Thorsten Eisenhofer, Konrad Rieck
LLM-based Vulnerability Discovery through the Lens of Code Metrics
Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer, Konrad Rieck
Adversarial Inputs for Linear Algebra Backends
Even the smallest number can make a big difference
Minor deviations in backend libraries like CUDA or MKL can cause identical AI models to produce different outputs. At ICML 2025, BIFOLD researcher Konrad Rieck showed how such subtle imprecisions can be exploited—posing a significant risk to AI system security.