Related papers: Privacy Amplification by Decentralization
Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…
Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct…
An algorithm is developed to gradually relax the Differential Privacy (DP) guarantee of a randomized response. The output from each relaxation maintains the same probability distribution as a standard randomized response with the equivalent…
This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data…
Decentralized optimization enables a network of agents to cooperatively optimize an overall objective function without a central coordinator and is gaining increased attention in domains as diverse as control, sensor networks, data mining,…
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…
Data privacy is an important concern in learning, when datasets contain sensitive information about individuals. This paper considers consensus-based distributed optimization under data privacy constraints. Consensus-based optimization…
Local differential privacy (LDP) has emerged as a gold-standard framework for privacy-preserving data analysis. However, characterizing the optimal privacy-utility trade-off (PUT) and the corresponding optimal LDP channels remains largely…
In Federated Learning (FL), multiple clients jointly train a machine learning model by sharing gradient information, instead of raw data, with a server over multiple rounds. To address the possibility of information leakage in spite of…
This paper considers subject level privacy in the FL setting, where a subject is an individual whose private information is embodied by several data items either confined within a single federation user or distributed across multiple…
We study locally differentially private algorithms for reinforcement learning to obtain a robust policy that performs well across distributed private environments. Our algorithm protects the information of local agents' models from being…
User-level privacy is important in distributed systems. Previous research primarily focuses on the central model, while the local models have received much less attention. Under the central model, user-level DP is strictly stronger than the…
Publishing graph statistics under node differential privacy has attracted much attention since it provides a stronger privacy guarantee than edge differential privacy. Existing works related to node differential privacy assume a trusted…
Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…
Local Differential Privacy (LDP) protocols allow an aggregator to obtain population statistics about sensitive data of a userbase, while protecting the privacy of the individual users. To understand the tradeoff between aggregator utility…
In this paper, we give an algorithm to publish the number of paths and Katz centrality under the local differential privacy (LDP), providing a thorough theoretical analysis. Although various works have already introduced subgraph counting…
Tensor-valued data, increasingly common in distributed big data applications like autonomous driving and smart healthcare, poses unique challenges for privacy protection due to its multidimensional structure and the risk of losing critical…
We consider a decentralized learning setting in which data is distributed over nodes in a graph. The goal is to learn a global model on the distributed data without involving any central entity that needs to be trusted. While gossip-based…
Local differential privacy (LDP) gives a strong privacy guarantee to be used in a distributed setting like federated learning (FL). LDP mechanisms in FL protect a client's gradient by randomizing it on the client; however, how can we…
We consider data release protocols for data $X=(S,U)$, where $S$ is sensitive; the released data $Y$ contains as much information about $X$ as possible, measured as $\operatorname{I}(X;Y)$, without leaking too much about $S$. We introduce…