We investigate practical and scalable algorithms for training large language models (LLMs)
with user-level differential privacy (DP) in order to provably safeguard all the examples …

Privacy attacks on Machine Learning (ML) models often focus on inferring the existence of
particular data points in the training data. However, what the adversary really wants to know …

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to
specialized tasks and applications. In this paper, we study the privacy implications of fine …

Auditing the use of data in training machine-learning (ML) models is an increasingly
pressing challenge, as myriad ML practitioners routinely leverage the effort of content …

This article introduces the Membership Inference Test (MINT), a novel approach that aims to
empirically assess if given data was used during the training of AI/ML models. Specifically …

The text-to-image models based on diffusion processes, capable of transforming text
descriptions into detailed images, have widespread applications in art, design, and beyond …

Data is a critical asset in AI, as high-quality datasets can significantly improve the
performance of machine learning models. In safety-critical domains such as autonomous …

Membership inference attacks allow adversaries to determine whether a particular example
was contained in the model's training dataset. While previous works have confirmed the …

Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage,
has become a well-accepted standard for privacy protection. Combined with powerful …

Machine learning models can leak private information about their training data, but the
standard methods to measure this risk, based on membership inference attacks (MIAs), have …