3 papers
cs.CR2025
Membership Inference Attacks on Sequence Models
Lorenzo Rossi, Michael Aerni, Jie Zhang +1
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tend…
cs.CL2024
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
Michael Aerni, Javier Rando, Edoardo Debenedetti +3
Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. B…
stat.ML2023
Strong inductive biases provably prevent harmless interpolation
Michael Aerni, Marco Milanta, Konstantin Donhauser +1
Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield small test error despite…