Banner Banner

Jonas Möller

Icon

Technische Universität Berlin
Machine Learning and Security (MLSec)

Ernst-Reuter-Platz 7, 10587 Berlin

Jonas Möller

Jonas Möller

Doctoral Researcher

Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer, Konrad Rieck

Adversarial Inputs for Linear Algebra Backends

July 13, 2025
https://www.mlsec.org/docs/2025-icml.pdf

News
Machine Learning| Jul 17, 2025

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.