Information about us, our actions, and our preferences is created at scale through surveys or
scientific studies or as a result of our interaction with digital devices such as smartphones …

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

Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the
risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a …

Deploying machine learning models in production may allow adversaries to infer sensitive
information about training data. There is a vast literature analyzing different types of …

While graph neural networks (GNNs) dominate the state-of-the-art for exploring graphs in
real-world applications, they have been shown to be vulnerable to a growing number of …

Abstract Algorithms such as Differentially Private SGD enable training machine learning
models with formal privacy guarantees. However, because these guarantees hold with …

Distribution inference, sometimes called property inference, infers statistical properties about
a training set from access to a model trained on that data. Distribution inference attacks can …

Membership inference (MI) attacks mainly aim to infer whether a data record was used to
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …

Privacy-preserving machine learning aims to train models on private data without leaking
sensitive information. Differential privacy (DP) is considered the gold standard framework for …

A large body of research has shown that machine learning models are vulnerable to
membership inference (MI) attacks that violate the privacy of the participants in the training …