Related papers: On the Power of Multiple Anonymous Messages
We consider a cell-free hybrid massive multiple-input multiple-output (MIMO) system with $K$ users and $M$ access points (APs), each with $N_a$ antennas and $N_r< N_a$ radio frequency (RF) chains. When $K\ll M{N_a}$, efficient uplink…
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution…
Privately counting distinct elements in a stream is a fundamental data analysis problem with many applications in machine learning. In the turnstile model, Jain et al. [NeurIPS2023] initiated the study of this problem parameterized by the…
The private simultaneous messages model is a non-interactive version of the multiparty secure computation, which has been intensively studied to examine the communication cost of the secure computation. We consider its quantum counterpart,…
Privacy is a central challenge for systems that learn from sensitive data sets, especially when a system's outputs must be continuously updated to reflect changing data. We consider the achievable error for differentially private continual…
Frequency estimation, a.k.a. histograms, is a workhorse of data analysis, and as such has been thoroughly studied under differentially privacy. In particular, computing histograms in the \emph{local} model of privacy has been the focus of a…
This paper establishes the fundamental limits of a multi-access system where multiple users communicate to a legitimate receiver in presence of an external warden. Only a specific subset of the users, called covert users, needs their…
Differentially private noise mechanisms commonly use symmetric noise distributions. This is attractive both for achieving the differential privacy definition, and for unbiased expectations in the noised answers. However, there are contexts…
Most of the literature on differential privacy considers the item-level case where each user has a single observation, but a growing field of interest is that of user-level privacy where each of the $n$ users holds $T$ observations and…
Federated learning (FL) enables edge devices to collaboratively train machine learning models, with model communication replacing direct data uploading. While over-the-air model aggregation improves communication efficiency, uploading…
We consider the problem of differentially private (DP) convex empirical risk minimization (ERM). While the standard DP-SGD algorithm is theoretically well-established, practical implementations often rely on shuffled gradient methods that…
We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and…
In this work, we consider a federated learning model in a wireless system with multiple base stations and inter-cell interference. We apply a differential private scheme to transmit information from users to their corresponding base station…
We study private broadcasting of two messages to two groups of receivers over independent parallel channels. One group consists of an arbitrary number of receivers interested in a common message, whereas the other group has only one…
Many proximity-based mobile social networks are developed to facilitate connections between any two people, or to help a user to find people with matched profile within a certain distance. A challenging task in these applications is to…
Secure aggregation is a foundational building block of privacy-preserving learning, yet achieving robustness under adversarial behavior remains challenging. Modern systems increasingly adopt the shuffle model of differential privacy…
Although robust learning and local differential privacy are both widely studied fields of research, combining the two settings is just starting to be explored. We consider the problem of estimating a discrete distribution in total variation…
This paper studies the problem of multi-agent computation under the differential privacy requirement of the agents' local datasets against eavesdroppers having node-to-node communications. We first propose for the network equipped with…
We consider the privacy problem of statistical estimation from distributed data, where users communicate to a central processor over a Gaussian multiple-access channel(MAC). To avoid the inevitable sacrifice of data utility for privacy in…
This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this one sample per client setup up including learning from fitness…