
Jonas Möller
Doctoral Researcher
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.