Related papers: On the Power of Multiple Anonymous Messages
Longitudinal data tracking under Local Differential Privacy (LDP) is a challenging task. Baseline solutions that repeatedly invoke a protocol designed for one-time computation lead to linear decay in the privacy or utility guarantee with…
The Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm supports the training of machine learning (ML) models with formal Differential Privacy (DP) guarantees. Traditionally, DP-SGD processes training data in batches using…
This paper studies the problem of secure communication over broadcast channels under the individual secrecy constraints. That is, the transmitter wants to send two independent messages to two legitimate receivers in the presence of an…
Messaging systems built on mesh networks consisting of smartphones communicating over Bluetooth have been used by protesters around the world after governments have disrupted Internet connectivity. Unfortunately, existing systems have been…
With changes in privacy laws, there is often a hard requirement for client data to remain on the device rather than being sent to the server. Therefore, most processing happens on the device, and only an altered element is sent to the…
We develop lower bounds for estimation under local privacy constraints---including differential privacy and its relaxations to approximate or R\'{e}nyi differential privacy---by showing an equivalence between private estimation and…
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…
A multiple-access channel is considered in which messages from one encoder are confidential. Confidential messages are to be transmitted with perfect secrecy, as measured by equivocation at the other encoder. The upper bounds and the…
Privacy-preserving voice protection approaches primarily suppress privacy-related information derived from paralinguistic attributes while preserving the linguistic content. Existing solutions focus particularly on single-speaker scenarios.…
This paper considers a multi-message secure aggregation with privacy problem, in which a server aims to compute $\sf K_c\geq 1$ linear combinations of local inputs from $\sf K$ distributed users. The problem addresses two tasks: (1)…
A basic model for key agreement with a remote (or hidden) source is extended to a multi-user model with joint secrecy and privacy constraints over all entities that do not trust each other after key agreement. Multiple entities using…
The turnstile continual release model of differential privacy captures scenarios where a privacy-preserving real-time analysis is sought for a dataset evolving through additions and deletions. In typical applications of real-time data…
We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific…
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world scenarios…
Differential privacy and sublinear algorithms are both rapidly emerging algorithmic themes in times of big data analysis. Although recent works have shown the existence of differentially private sublinear algorithms for many problems…
This paper is motivated by applications of a Census Bureau interested in releasing aggregate socio-economic data about a large population without revealing sensitive information about any individual. The released information can be the…
Recent increase in online privacy concerns prompts the following question: can a recommender system be accurate if users do not entrust it with their private data? To answer this, we study the problem of learning item-clusters under local…
A common goal of privacy research is to release synthetic data that satisfies a formal privacy guarantee and can be used by an analyst in place of the original data. To achieve reasonable accuracy, a synthetic data set must be tuned to…
Differential privacy provides a theoretical framework for processing a dataset about $n$ users, in a way that the output reveals a minimal information about any single user. Such notion of privacy is usually ensured by noise-adding…
In recent years, it has come to attention that governments have been doing mass surveillance of personal communications without the consent of the citizens. As a consequence of these revelations, developers have begun releasing new…