Machine learning (ML) models have been widely applied to various applications, including
image classification, text generation, audio recognition, and graph data analysis. However …

A membership inference attack allows an adversary to query a trained machine learning
model to predict whether or not a particular example was contained in the model's training …

How much does a machine learning algorithm leak about its training data, and why?
Membership inference attacks are used as an auditing tool to quantify this leakage. In this …

We introduce a new class of attacks on machine learning models. We show that an
adversary who can poison a training dataset can cause models trained on this dataset to …

Modern neural language models that are widely used in various NLP tasks risk memorizing
sensitive information from their training data. Understanding this memorization is important …

Synthetic data has been advertised as a silver-bullet solution to privacy-preserving data
publishing that addresses the shortcomings of traditional anonymisation techniques. The …

The advent of the Internet of Things (IoT) has brought forth an era of unprecedented
connectivity, with an estimated 80 billion smart devices expected to be in operation by the …

Machine learning models exhibit two seemingly contradictory phenomena: training data
memorization, and various forms of forgetting. In memorization, models overfit specific …

Membership inference attacks are designed to determine, using black box access to trained
models, whether a particular example was used in training or not. Membership inference …

This is the first survey of the active area of AI research that focuses on privacy issues in
Large Language Models (LLMs). Specifically, we focus on work that red-teams models to …