Követés
Michael Aerni
Michael Aerni
Doctoral student at Secure and Private AI (SPY) Lab, ETH Zurich
E-mail megerősítve itt: inf.ethz.ch - Kezdőlap
Cím
Hivatkozott rá
Hivatkozott rá
Év
Evaluations of Machine Learning Privacy Defenses are Misleading
M Aerni, J Zhang, F Tramèr
ACM SIGSAC Conference on Computer and Communications Security, 1271-1284, 2024
212024
Interpolation can hurt robust generalization even when there is no noise
K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang
Advances in Neural Information Processing Systems 34, 23465-23477, 2021
132021
Strong inductive biases provably prevent harmless interpolation
M Aerni, M Milanta, K Donhauser, F Yang
International Conference on Learning Representations (ICLR), 2023
102023
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
M Aerni, J Rando, E Debenedetti, N Carlini, D Ippolito, F Tramèr
arXiv preprint arXiv:2411.10242, 2024
2024
Maximizing the robust margin provably overfits on noiseless data
K Donhauser, A Tifrea, M Aerni, R Heckel, F Yang
ICML 2021 Workshop on Adversarial Machine Learning, 2021
2021
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–5