Corpus ID: 236493699

Secure Bayesian Federated Analytics for Privacy-Preserving Trend Detection

  title={Secure Bayesian Federated Analytics for Privacy-Preserving Trend Detection},
  author={Amit Chaulwar and Michael Huth},
Federated analytics has many applications in edge computing, its use can lead to better decision making for service provision, product development, and user experience. We propose a Bayesian approach to trend detection in which the probability of a keyword being trendy, given a dataset, is computed via Bayes’ Theorem; the probability of a dataset, given that a keyword is trendy, is computed through secure aggregation of such conditional probabilities over local datasets of users. We propose a… Expand

Figures and Tables from this paper


Federated Heavy Hitters Discovery with Differential Privacy
A distributed and privacy-preserving algorithm for discovering the heavy hitters in a population of user-generated data streams that eliminates the need to centralize raw data while also avoiding the significant loss in utility incurred by local differential privacy. Expand
Practical Secure Aggregation for Privacy-Preserving Machine Learning
This protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner, and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. Expand
Secure MPC for Analytics as a Web Application
Secure multi-party computation (MPC) resolves this tension: aggregate data may be computed while protecting each contributor’s confidentiality, and recent efforts aim to deliver them to end-users. Expand
Sharemind: A Framework for Fast Privacy-Preserving Computations
This paper presents a provably secure and efficient general-purpose computation system to address the problem of gathering and processing sensitive data and provides significantly increased privacy preservation when compared to standard centralised databases. Expand
Private Dataset Generation Using Privacy Preserving Collaborative Learning
This work introduces a privacy preserving FedCollabNN framework for training machine learning models at edge, which is computationally efficient and robust against adversarial attacks. Expand
Private FL-GAN: Differential Privacy Synthetic Data Generation Based on Federated Learning
Private FL-GAN, a differential privacy generative adversarial network model based on federated learning, is proposed, which can generate high-quality synthetic data without sacrificing the privacy of the training data. Expand
Privacy-preserving deep learning
  • R. Shokri, Vitaly Shmatikov
  • Computer Science
  • 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2015
This paper presents a practical system that enables multiple parties to jointly learn an accurate neural-network model for a given objective without sharing their input datasets, and exploits the fact that the optimization algorithms used in modern deep learning, namely, those based on stochastic gradient descent, can be parallelized and executed asynchronously. Expand
Monitoring Trends on Facebook
This paper proposes and evaluates a system for trend detection based on the characteristics of the posts shared on Face book, and proposes three categories of trending topics: 'disruptive events', 'popular topics' and 'daily routines'. Expand
Federated Learning Of Out-Of-Vocabulary Words
We demonstrate that a character-level recurrent neural network is able to learn out-of-vocabulary (OOV) words under federated learning settings, for the purpose of expanding the vocabulary of aExpand
Recent Approaches for Trend Detection from Text Documents and Real Time Streams-A Study
This paper traces the different methods and systems that are being currently utilized for detecting trends from textual data and social data and traces the major content in text documents and social networking websites. Expand