Introducing Command R+: Our new, most powerful model in the Command R family.
Date: Mar 02, 2024
Time: 6:00 PM - 7:00 PM
Location: Online
Join the NLP group as they welcome Anshuman Suri to present "Do Membership Inference Attacks Work on Large Language Models?" (https://arxiv.org/abs/2402.07841)
Abstract:
Membership inference attacks (MIAs) aim to discern whether a specific data point belongs to the training data of a target model. While extensive research has addressed MIAs in traditional machine learning models, limited attention has been paid to their study in the pre-training data of large language models (LLMs). In this presentation, I will discuss our investigation into MIAs across a range of LLMs trained on the Pile dataset. Our findings indicate that MIAs only marginally outperform random guessing across various model sizes and domains. I will then delve into how the observed poor performance can be attributed to the unique characteristics of LLM training and the interpretation of membership within text-based generative models.
Add event to calendar