Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning

@article{Yang2022BlinderEP,
  title={Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning},
  author={Xin Yang and Omid Ardakanian},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.12046}
}
This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the collected sensor data have different underlying distributions. Our anonymization model, dubbed Blinder, is based on a variational autoencoder and discriminator networks trained in an adversarial fashion. We use the model-agnostic meta-learning framework to adapt the anonymization model trained via… 

References

SHOWING 1-10 OF 63 REFERENCES

Human Daily Activity and Fall Recognition Using a Smartphone's Acceleration Sensor

This article presents the results of a comprehensive evaluation of using a smartphone’s acceleration sensor for human activity and fall recognition, including 12 different types of activities of daily living (ADLs) and 4 different type of falls, recorded from 66 subjects in the context of creating “MobiAct”, a publicly available dataset for benchmarking and developing human activityand fall recognition systems.

PPFL: privacy-preserving federated learning with trusted execution environments

A Privacy-preserving Federated Learning (PPFL) framework for mobile systems to limit privacy leakages in federated learning, which can successfully defend the trained model against data reconstruction, property inference, and membership inference attacks.

PyTorch: An Imperative Style, High-Performance Deep Learning Library

This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance.

Mobile sensor data anonymization

This work forms the anonymization problem using an information-theoretic approach and proposes a new multi-objective loss function for training deep autoencoders that helps minimizing user-identity information as well as data distortion to preserve the application-specific utility.

Communication-Efficient Learning of Deep Networks from Decentralized Data

This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

Semi-supervised Learning with Deep Generative Models

It is shown that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.

Auto-Encoding Variational Bayes

A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.

ObscureNet: Learning Attribute-invariant Latent Representation for Anonymizing Sensor Data

In this paper, we introduce ObscureNet, an encoder-decoder architecture that effectively conceals private attributes associated with time series data generated by sensors in IoT devices, while

Privacy-Preserving Feature Selection with Secure Multiparty Computation

This work proposes the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features.

DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones

An adversarial training framework, DeepObfuscator, which prevents the usage of the features for reconstruction of the raw images and inference of private attributes, and includes a learnable encoder that is designed to hide privacy-related sensitive information from the features by performing the proposed adversarialTraining algorithm.
...