Related papers: Privacy Amplification via Shuffled Check-Ins

As large-scale theft of data from corporate servers is becoming increasingly common, it becomes interesting to examine alternatives to the paradigm of centralizing sensitive data into large databases. Instead, one could use cryptography and…

The framework of differential privacy protects an individual's privacy while publishing query responses on congregated data. In this work, a new noise addition mechanism for differential privacy is introduced where the noise added is…

Privacy preservation in distributed computations is an important subject as digitization and new technologies enable collection and storage of vast amounts of data, including private data belonging to individuals. To this end, there is a…

Decentralized optimization is gaining increased traction due to its widespread applications in large-scale machine learning and multi-agent systems. The same mechanism that enables its success, i.e., information sharing among participating…

We develop a sharp, experiment-level privacy theory for amplification by shuffling in the Gaussian regime: a fixed finite-output local randomizer with full support and neighboring binary datasets differing in one user. We first prove exact…

In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involved individuals. This is achieved by randomly perturbing the…

Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning…

The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty. Unfortunately, sharing model updates also creates…

Trustworthy federated learning aims to achieve optimal performance while ensuring clients' privacy. Existing privacy-preserving federated learning approaches are mostly tailored for image data, lacking applications for time series data,…

Differential privacy (DP) is a formal notion for quantifying the privacy loss of algorithms. Algorithms in the central model of DP achieve high accuracy but make the strongest trust assumptions whereas those in the local DP model make the…

A protocol by Ishai et al.\ (FOCS 2006) showing how to implement distributed $n$-party summation from secure shuffling has regained relevance in the context of the recently proposed \emph{shuffle model} of differential privacy, as it allows…

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the…

Differential privacy (DP) is widely employed to provide privacy protection for individuals by limiting information leakage from the aggregated data. Two well-known models of DP are the central model and the local model. The former requires…

We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation (DME). We develop a…

We develop formal privacy mechanisms for releasing statistics from data with many outlying values, such as income data. These mechanisms ensure that a per-record differential privacy guarantee degrades slowly in the protected records'…

Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring…

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…

The shuffle model is recently proposed to address the issue of severe utility loss in Local Differential Privacy (LDP) due to distributed data randomization.In the shuffle model, a shuffler is utilized to break the link between the user…

Privacy-preserving distributed processing has recently attracted considerable attention. It aims to design solutions for conducting signal processing tasks over networks in a decentralized fashion without violating privacy. Many algorithms…

Recommender systems are widely used. Usually, recommender systems are based on a centralized client-server architecture. However, this approach implies drawbacks regarding the privacy of users. In this paper, we propose a distributed…