Aerni, Michael

4 publications

ICLR 2025 Measuring Non-Adversarial Reproduction of Training Data in Large Language Models Michael Aerni, Javier Rando, Edoardo Debenedetti, Nicholas Carlini, Daphne Ippolito, Florian Tramèr

ICLR 2023 Strong Inductive Biases Provably Prevent Harmless Interpolation Michael Aerni, Marco Milanta, Konstantin Donhauser, Fanny Yang

NeurIPS 2021 Interpolation Can Hurt Robust Generalization Even When There Is No Noise Konstantin Donhauser, Alexandru Tifrea, Michael Aerni, Reinhard Heckel, Fanny Yang

ICMLW 2021 Maximizing the Robust Margin Provably Overfits on Noiseless Data Konstantin Donhauser, Alexandru Tifrea, Michael Aerni, Reinhard Heckel, Fanny Yang