A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics

@article{Osia2020AHD,
  title={A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics},
  author={Seyed Ali Osia and Ali Shahin Shamsabadi and Sina Sajadmanesh and Ali Taheri and Kleomenis Katevas and Hamid R. Rabiee and Nicholas D. Lane and Hamed Haddadi},
  journal={IEEE Internet of Things Journal},
  year={2020},
  volume={7},
  pages={4505-4518}
}
Internet-of-Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models… Expand
Local Differential Privacy for Deep Learning
TLDR
A new local differentially private (LDP) algorithm named LATENT is proposed that redesigns the training process and enables a data owner to add a randomization layer before data leave the data owners’ devices and reach a potentially untrusted machine learning service. Expand
FORESEEN: Towards Differentially Private Deep Inference for Intelligent Internet of Things
TLDR
This work proposes a FOg-based pRivacy prEServing dEep lEarNing framework named FORESEEN, capable of reducing the communication cost and providing inherent support for robustness and scalability, and builds deep models with mixed-precision. Expand
Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
TLDR
A noisy training method is proposed to enhance the cloud-side network robustness to perturbed data and can not only preserve privacy but also improve the inference performance. Expand
DataMix: Efficient Privacy-Preserving Edge-Cloud Inference
TLDR
This paper mediate between the resource-constrained edge devices and the privacy-invasive cloud servers by introducing a novel privacy-preserving edge-cloud inference framework, DataMix, which off-load the majority of the computations to the cloud and leverage a pair of mixing and de-mixing operation, inspired by mixup. Expand
Differentially Private Collaborative Learning for the IoT Edge
TLDR
The design of a privacy-preserving collaborative learning approach, in which the edge devices and the cloud train different stages of a deep neural network, and the data transmitted from an edge device to the honest-but-curious cloud is perturbed by Laplacian random noises to achieve e-differential privacy is presented. Expand
PrivStream: Enabling Privacy-Preserving Inferences on IoT Data Stream at the Edge
  • D. Wang, Ju Ren, +4 authors Xuemin Shen
  • Computer Science
  • 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
  • 2019
TLDR
The experimental results based on realistic IoT data stream demonstrate that Privstream can preserve the data utility of useful inferences and mitigate the sensitive inferences simultaneously with efficient system overheads. Expand
Privacy-Preserving Computation Offloading for Parallel Deep Neural Networks Training
TLDR
An alternative DNN training strategy for resource-limited users is proposed with the help of an untrusted server, and a differentially private activation algorithm is designed for end users to ensure the privacy of the offloading after model separation. Expand
Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
  • M. Malekzadeh, R. Clegg, H. Haddadi
  • Computer Science, Mathematics
  • 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)
  • 2018
TLDR
This paper introduces Replacement AutoEncoder, a novel feature-learning algorithm which learns how to transform discriminative features of multi-variate time-series that correspond to sensitive inferences, into some features that have been more observed in non-sensitive inferences to protect users' privacy. Expand
Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
TLDR
This paper proposes deterministic and probabilistic transformations in the latent space of a variational autoencoder to synthesize time series data such that intrusive inferences are prevented while desired inferences can still be made with sufficient accuracy. Expand
Privacy-preserving Data Analysis through Representation Learning and Transformation
TLDR
This paper proposes probabilistic transformations in the latent space of a variational autoencoder to synthesize time series data such that intrusive inferences are prevented while desired inferences can still be made with a satisfactory level of accuracy. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 70 REFERENCES
Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
  • M. Malekzadeh, R. Clegg, H. Haddadi
  • Computer Science, Mathematics
  • 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)
  • 2018
TLDR
This paper introduces Replacement AutoEncoder, a novel feature-learning algorithm which learns how to transform discriminative features of multi-variate time-series that correspond to sensitive inferences, into some features that have been more observed in non-sensitive inferences to protect users' privacy. Expand
Can Deep Learning Revolutionize Mobile Sensing?
TLDR
Preliminary answers to how the field of mobile sensing can best make use of advances in deep learning towards robust and efficient sensor inference are provided by prototyping a low-power Deep Neural Network inference engine that exploits both the CPU and DSP of a mobile device SoC. Expand
A Privacy-Preserving Deep Learning Approach for Face Recognition with Edge Computing
TLDR
This paper utilizes the differentially private mechanism to enable the privacy-preserving edge based training of DNN face recognition models, and shows that the mechanism is capable of training models in different scenarios, e.g., from scratch, or through finetuning over existed models. Expand
Privacy-preserving deep learning
  • R. Shokri, Vitaly Shmatikov
  • Computer Science
  • 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
  • 2015
TLDR
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
Deep Learning in Mobile and Wireless Networking: A Survey
TLDR
This paper bridges the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas, and provides an encyclopedic review of mobile and Wireless networking research based on deep learning, which is categorize by different domains. Expand
SecureML: A System for Scalable Privacy-Preserving Machine Learning
TLDR
This paper presents new and efficient protocols for privacy preserving machine learning for linear regression, logistic regression and neural network training using the stochastic gradient descent method, and implements the first privacy preserving system for training neural networks. Expand
Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables
TLDR
This paper proposes SparseSep, a new approach that leverages the sparsification of fully connected layers and separation of convolutional kernels to reduce the resource requirements of popular deep learning algorithms, and allows large-scale DNNs and CNNs to run efficiently on mobile and embedded hardware with only minimal impact on inference accuracy. Expand
ZOE: A Cloud-less Dialog-enabled Continuous Sensing Wearable Exploiting Heterogeneous Computation
TLDR
A match-box sized collar- or lapel-worn sensor that pushes the boundary of wearables in an important set of new directions, ZOE aims to perform multiple deep sensor inferences that span key aspects of everyday life on continuously sensed data; while also offering this data not only within conventional analytics but also through a speech dialog system that is able to answer impromptu casual questions from users. Expand
Federated Learning: Strategies for Improving Communication Efficiency
TLDR
Two ways to reduce the uplink communication costs are proposed: structured updates, where the user directly learns an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, which learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling. Expand
Advanced Media-Based Smart Big Data on Intelligent Cloud Systems
TLDR
The proposed encoding algorithm outperforms the conventional HEVC standard which demonstrated by the performance evaluations and could be used and integrated into HEVC, as a Smart Big Data, without violating the standard. Expand
...
1
2
3
4
5
...