PrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
- URL: http://arxiv.org/abs/2309.12483v2
- Date: Fri, 12 Apr 2024 06:44:29 GMT
- Title: PrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
- Authors: Johannes Liebenow, Timothy Imort, Yannick Fuchs, Marcel Heisel, Nadja Käding, Jan Rupp, Esfandiar Mohammadi,
- Abstract summary: We present a toolchain called PrivAgE for a distributed, privacy-preserving aggregation of local data.
The distributed aggregation is based on secure summation and simultaneously satisfies the notion of differential privacy.
We demonstrate the flexibility of our toolchain by presenting an extension of the summation of histograms to distributed clustering.
- Score: 0.5216865930622505
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Valuable insights, such as frequently visited environments in the wake of the COVID-19 pandemic, can oftentimes only be gained by analyzing sensitive data spread across edge-devices like smartphones. To facilitate such an analysis, we present a toolchain called PrivAgE for a distributed, privacy-preserving aggregation of local data by taking the limited resources of edge-devices into account. The distributed aggregation is based on secure summation and simultaneously satisfies the notion of differential privacy. In this way, other parties can neither learn the sensitive data of single clients nor a single client's influence on the final result. We perform an evaluation of the power consumption, the running time and the bandwidth overhead on real as well as simulated devices and demonstrate the flexibility of our toolchain by presenting an extension of the summation of histograms to distributed clustering.
Related papers
- PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a.
Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns.
We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z) - Ungeneralizable Examples [70.76487163068109]
Current approaches to creating unlearnable data involve incorporating small, specially designed noises.
We extend the concept of unlearnable data to conditional data learnability and introduce textbfUntextbfGeneralizable textbfExamples (UGEs)
UGEs exhibit learnability for authorized users while maintaining unlearnability for potential hackers.
arXiv Detail & Related papers (2024-04-22T09:29:14Z) - Privacy Amplification for the Gaussian Mechanism via Bounded Support [64.86780616066575]
Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset.
We propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting.
arXiv Detail & Related papers (2024-03-07T21:22:07Z) - Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification [54.1447806347273]
Amplification by subsampling is one of the main primitives in machine learning with differential privacy.
We propose the first general framework for deriving mechanism-specific guarantees.
We analyze how subsampling affects the privacy of groups of multiple users.
arXiv Detail & Related papers (2024-03-07T19:36:05Z) - Cross-Network Social User Embedding with Hybrid Differential Privacy
Guarantees [81.6471440778355]
We propose a Cross-network Social User Embedding framework, namely DP-CroSUE, to learn the comprehensive representations of users in a privacy-preserving way.
In particular, for each heterogeneous social network, we first introduce a hybrid differential privacy notion to capture the variation of privacy expectations for heterogeneous data types.
To further enhance user embeddings, a novel cross-network GCN embedding model is designed to transfer knowledge across networks through those aligned users.
arXiv Detail & Related papers (2022-09-04T06:22:37Z) - Privacy-Aware Compression for Federated Data Analysis [31.970815289473965]
Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of low-bandwidth user devices to estimate aggregate statistics.
Two major challenges in this framework are privacy, since user data is often sensitive, and compression, since the user devices have low network bandwidth.
We take a holistic look at the problem and design a family of privacy-aware compression mechanisms that work for any given communication budget.
arXiv Detail & Related papers (2022-03-15T17:57:13Z) - Towards Sparse Federated Analytics: Location Heatmaps under Distributed
Differential Privacy with Secure Aggregation [15.569382274788234]
We design a scalable algorithm to privately generate location heatmaps over decentralized data from millions of user devices.
It aims to ensure differential privacy before data becomes visible to a service provider while maintaining high data accuracy and minimizing resource consumption on users' devices.
arXiv Detail & Related papers (2021-11-03T17:19:05Z) - The Distributed Discrete Gaussian Mechanism for Federated Learning with
Secure Aggregation [28.75998313625891]
We present a comprehensive end-to-end system, which appropriately discretizes the data and adds discrete Gaussian noise before performing secure aggregation.
Our theoretical guarantees highlight the complex tension between communication, privacy, and accuracy.
arXiv Detail & Related papers (2021-02-12T08:20:18Z) - Generating private data with user customization [9.415164800448853]
Mobile devices can produce and store large amounts of data that can enhance machine learning models.
However, this data may contain private information specific to the data owner that prevents the release of the data.
We want to reduce the correlation between user-specific private information and the data while retaining the useful information.
arXiv Detail & Related papers (2020-12-02T19:13:58Z) - Deep Directed Information-Based Learning for Privacy-Preserving Smart
Meter Data Release [30.409342804445306]
We study the problem in the context of time series data and smart meters (SMs) power consumption measurements.
We introduce the Directed Information (DI) as a more meaningful measure of privacy in the considered setting.
Our empirical studies on real-world data sets from SMs measurements in the worst-case scenario show the existing trade-offs between privacy and utility.
arXiv Detail & Related papers (2020-11-20T13:41:11Z) - Graph-Homomorphic Perturbations for Private Decentralized Learning [64.26238893241322]
Local exchange of estimates allows inference of data based on private data.
perturbations chosen independently at every agent, resulting in a significant performance loss.
We propose an alternative scheme, which constructs perturbations according to a particular nullspace condition, allowing them to be invisible.
arXiv Detail & Related papers (2020-10-23T10:35:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.