We explore machine unlearning (MU) in the domain of large language models (LLMs),
referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence …

Membership inference (MI) attacks try to determine if a data sample was used to train a
machine learning model. For foundation models trained on unknown Web data, MI attacks …

While large language models (LLMs) present significant potential for supporting numerous
real-world applications and delivering positive social impacts, they still face significant …

The rapid scaling of large language models (LLMs) has raised concerns about the
transparency and fair use of the pretraining data used for training them. Detecting such …

Large Language Models (LLMs) have demonstrated impressive capabilities in generating
diverse and contextually rich text. However, concerns regarding copyright infringement arise …

We consider the problem of a training data proof, where a data creator or owner wants to
demonstrate to a third party that some machine learning model was trained on their data …

Unlearning methods have the potential to improve the privacy and safety of large language
models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning …

The performance differential of large language models (LLM) between languages hinders
their effective deployment in many regions, inhibiting the potential economic and societal …

As the scale of training corpora for large language models (LLMs) grows, model developers
become increasingly reluctant to disclose details on their data. This lack of transparency …

The training data in large language models is key to their success, but it also presents
privacy and security risks, as it may contain sensitive information. Detecting pre-training data …