Dr. Thorsten Eisenhofer
Dr. Thorsten Eisenhofer
Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer, Konrad Rieck
Adversarial Inputs for Linear Algebra Backends
David Beste, Grégoire Menguy, Hossein Hajipour, Mario Fritz, Antonio Emanuele Cinà, Sébastien Bardin, Thorsten Holz, Thorsten Eisenhofer & Lea Schönherr
Exploring the Potential of LLMs for Code Deobfuscation
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer, Paul Grubbs, Nicolas Papernot
Learned-Database Systems Security
Erik Imgrund, Thorsten Eisenhofer, Konrad Rieck
Adversarial Observations in Weather Forecasting
Felix Weissberg, Thorsten Eisenhofer, Jan Malte Hilgefort, Martin Eisemann, Steve Grogorick, Daniel Arp, Konrad Rieck
Seeing Through: Analyzing and Attacking Virtual Backgrounds in Video Calls
IEEE SaTML 2025 Conference Contribution
Dr. Thorsten Eisenhofer will present the paper “Verifiable and Provably Secure Machine Unlearning,” at SaTML 2025. Eisenhofer is Postdoc in the research group “Machine Learning and Security”. His paper introduces a new framework designed to verify that user data has been correctly deleted from machine learning models, supported by cryptographic proofs.