Related papers: Private Linear Transformation: The Individual Priv…
We consider a setup in which confidential i.i.d. samples $X_1,\dotsc,X_n$ from an unknown finite-support distribution $\boldsymbol{p}$ are passed through $n$ copies of a discrete privatization channel (a.k.a. mechanism) producing outputs…
We initiate the study of a new model of supervised learning under privacy constraints. Imagine a medical study where a dataset is sampled from a population of both healthy and unhealthy individuals. Suppose healthy individuals have no…
The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that…
The collection of individuals' data has become commonplace in many industries. Local differential privacy (LDP) offers a rigorous approach to preserving privacy whereby the individual privatises their data locally, allowing only their…
Computing the principal component (PC) of the adjacency matrix of an undirected graph has several applications ranging from identifying key vertices for influence maximization and controlling diffusion processes, to discovering densely…
Differential privacy (DP) is a formal notion that restricts the privacy leakage of an algorithm when running on sensitive data, in which privacy-utility trade-off is one of the central problems in private data analysis. In this work, we…
This paper introduces a generalization of the Private Information Retrieval with Side Information (PIR-SI) problem called Popularity-Aware PIR-SI (PA-PIR-SI). The PA-PIR-SI problem includes one or more remote servers storing copies of a…
Nonlinear aggregation is central to modern distributed systems, yet its privacy behavior is far less understood than that of linear aggregation. Unlike linear aggregation where mature mechanisms can often suppress information leakage,…
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for local…
As a prevailing collaborative filtering method for recommendation systems, one-bit matrix completion requires data collected by users to provide personalized service. Due to insidious attacks and unexpected inference, the release of users'…
We introduce the \emph{Private Contiguous-Block Retrieval (PCBR)} problem, where a user retrieves a block of $D$ messages with contiguous indices from $K$ replicated messages stored across $N$ non-colluding servers, while hiding the…
Federated learning (FL) is a collaborative learning paradigm for decentralized private data from mobile terminals (MTs). However, it suffers from issues in terms of communication, resource of MTs, and privacy. Existing privacy-preserving FL…
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…
The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…
We propose three private information retrieval (PIR) protocols for distributed storage systems (DSSs) where data is stored using an arbitrary linear code. The first two protocols, named Protocol 1 and Protocol 2, achieve privacy for the…
Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally…
Multi-server single-message private information retrieval is studied in the presence of side information. In this problem, $K$ independent messages are replicatively stored at $N$ non-colluding servers. The user wants to privately download…
Consider the following problem: given a metric space, some of whose points are "clients", open a set of at most $k$ facilities to minimize the average distance from the clients to these facilities. This is just the well-studied $k$-median…
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each…
Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…