Related papers: Differentially Private Synthetic Data via Foundati…

The increasing availability of personal data has enabled significant advances in fields such as machine learning, healthcare, and cybersecurity. However, this data abundance also raises serious privacy concerns, especially in light of…

Local differential privacy~(LDP) is an information-theoretic privacy definition suitable for statistical surveys that involve an untrusted data curator. An LDP version of quasi-maximum likelihood estimator~(QMLE) has been developed, but the…

We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of…

The analysis of the privacy properties of Privacy-Preserving Ads APIs is an area of research that has received strong interest from academics, industry, and regulators. Despite this interest, the empirical study of these methods is hindered…

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…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data…

Differential privacy (DP) provides a principled approach to synthesizing data (e.g., loads) from real-world power systems while limiting the exposure of sensitive information. However, adversaries may exploit synthetic data to calibrate…

Creation of a synthetic dataset that faithfully represents the data distribution and simultaneously preserves privacy is a major research challenge. Many space partitioning based approaches have emerged in recent years for answering…

We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in…

Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm…

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our…

We study locally differentially private algorithms for reinforcement learning to obtain a robust policy that performs well across distributed private environments. Our algorithm protects the information of local agents' models from being…

The introduction and advancements in Local Differential Privacy (LDP) variants have become a cornerstone in addressing the privacy concerns associated with the vast data produced by smart devices, which forms the foundation for data-driven…

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…

Local Differential Privacy (LDP) provides provable privacy protection for data collection without the assumption of the trusted data server. In the real-world scenario, different data have different privacy requirements due to the distinct…

Modern machine learning systems achieve great success when trained on large datasets. However, these datasets usually contain sensitive information (e.g. medical records, face images), leading to serious privacy concerns. Differentially…

Personalizing large-scale diffusion models poses serious privacy risks, especially when adapting to small, sensitive datasets. A common approach is to fine-tune the model using differentially private stochastic gradient descent (DP-SGD),…

In differential privacy (DP), a challenging problem is to generate synthetic datasets that efficiently capture the useful information in the private data. The synthetic dataset enables any task to be done without privacy concern and…