相关论文: Unifying Re-Identification, Attribute Inference, a…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Differential privacy (DP) techniques can be applied to the federated learning model to statistically guarantee data privacy against inference attacks to communication among the learning agents. While ensuring strong data privacy, however,…

In this paper, we provide two views of constrained differential private (DP) mechanisms. The first one is as belief revision. A constrained DP mechanism is obtained by standard probabilistic conditioning, and hence can be naturally…

Mobility data is essential for cities and communities to identify areas for necessary improvement. Data collected by mobility providers already contains all the information necessary, but privacy of the individuals needs to be preserved.…

As the use of differential privacy (DP) becomes widespread, the development of effective tools for reasoning about the privacy guarantee becomes increasingly critical. In pursuit of this goal, we demonstrate novel relationships between DP…

User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy…

Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis. It is well-known that the cost of adding DP to deep learning model is its accuracy. However, it remains unclear how it affects…

Differential Privacy (DP) considers a scenario in which an adversary has almost complete information about the entries of a database. This worst-case assumption is likely to overestimate the privacy threat faced by an individual in…

The superior performance of large foundation models relies on the use of massive amounts of high-quality data, which often contain sensitive, private and copyrighted material that requires formal protection. While differential privacy (DP)…

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

The shuffle model of Differential Privacy (DP) is an enhanced privacy protocol which introduces an intermediate trusted server between local users and a central data curator. It significantly amplifies the central DP guarantee by…

Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms that achieve an optimal trade-off between privacy, utility and…

Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remains a critical…

Differential privacy (DP) has become the de facto standard for protecting sensitive data, providing strong guarantees that published statistics or models reveal limited information about any individual. However, privacy noise and restricted…

The paper redefines econometric identification under formal privacy constraints, particularly differential privacy (DP). Traditionally, econometrics focuses on point or partial identification, aiming to recover parameters precisely or…

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 (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its non-private counterpart. To analyze the convergence of DP…

Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via…

Differentially private (DP) machine learning algorithms incur many sources of randomness, such as random initialization, random batch subsampling, and shuffling. However, such randomness is difficult to take into account when proving…

This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks. First, we propose to quantitatively measure the trade-off between model accuracy and privacy losses…