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

As machine learning becomes more widely used, the need to study its implications in
security and privacy becomes more urgent. Although the body of work in privacy has been …

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 …

Diffusion-based generative models have shown great potential for image synthesis, but
there is a lack of research on the security and privacy risks they may pose. In this paper, we …

Abstract Empirical attacks on Federated Learning (FL) systems indicate that FL is fraught
with numerous attack surfaces throughout the FL execution. These attacks can not only …

Differentially private (DP) machine learning allows us to train models on private data while
limiting data leakage. DP formalizes this data leakage through a cryptographic game, where …

Machine learning (ML) has been widely adopted in various privacy-critical applications, eg,
face recognition and medical image analysis. However, recent research has shown that ML …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

This paper studies extractable memorization: training data that an adversary can efficiently
extract by querying a machine learning model without prior knowledge of the training …