WS-2024-0010

In some settings, an adversary can perform a training data extraction attack to recover individual training examples by querying the language model. It finds that larger models are more vulnerable than smaller models...

WS-2024-0007

In some settings, an adversary can perform a training data extraction attack to recover individual training examples by querying the language model. It finds that larger models are more vulnerable than smaller models...

Extracting Personal Information from Large Language Models Like GPT-2

Researchers have been able to find all sorts of personal information within GPT-2. This information was part of the training data, and can be extracted with the right sorts of queries. Paper: "Extracting Training Data from Large Language Models." Abstract: It has become common to publish large...