Related papers: Differentially Private Auditing Under Strategic Re…

Differential privacy (DP) is a widely used notion for reasoning about privacy when publishing aggregate data. In this paper, we observe that certain DP mechanisms are amenable to a posteriori privacy analysis that exploits the fact that…

We study black-box auditing for machine learning algorithms that claim R \ 'enyi differential privacy (RDP) guarantees. We introduce an auditing framework, based on hypothesis testing, that directly estimates R\'enyi divergence between…

Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy (DP). Apple's DifferentialPrivacy framework is deployed across its operating systems and handles sensitive…

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…

We present an optimization framework for solving multi-agent nonlinear programs subject to inequality constraints while keeping the agents' state trajectories private. Each agent has an objective function depending only upon its own state…

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

Differential Privacy (DP) has emerged as a pivotal approach for safeguarding individual privacy in data analysis, yet its practical adoption is often hindered by challenges in the implementation and communication of DP. This paper presents…

Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentially private versions of them. However, their conversion to…

Differential privacy (DP) provides a provable framework for protecting individuals by customizing a random mechanism over a privacy-sensitive dataset. Deep learning models have demonstrated privacy risks in model exposure as an established…

Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…

When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that…

Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the…

Differentially private synthetic data generation (DP-SDG) algorithms are used to release datasets that are structurally and statistically similar to sensitive data while providing formal bounds on the information they leak. However, bugs in…

Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are…

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Companies increasingly expose machine learning (ML) models trained over sensitive user data to untrusted domains, such as end-user devices and wide-access model stores. We present Sage, a differentially private (DP) ML platform that bounds…

Cross-attention has emerged as a cornerstone module in modern artificial intelligence, underpinning critical applications such as retrieval-augmented generation (RAG), system prompting, and guided stable diffusion. However, this is a rising…