Prive-HD: Privacy-Preserved Hyperdimensional Computing

05/14/2020
by   Behnam Khaleghi, et al.
0

The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted inference inevitable. Sending private information to remote servers makes the privacy of inference also vulnerable because of susceptible communication channels or even untrustworthy hosts. In this paper, we target privacy-preserving training and inference of brain-inspired Hyperdimensional (HD) computing, a new learning algorithm that is gaining traction due to its light-weight computation and robustness particularly appealing for edge devices with tight constraints. Indeed, despite its promising attributes, HD computing has virtually no privacy due to its reversible computation. We present an accuracy-privacy trade-off method through meticulous quantization and pruning of hypervectors, the building blocks of HD, to realize a differentially private model as well as to obfuscate the information sent for cloud-hosted inference. Finally, we show how the proposed techniques can be also leveraged for efficient hardware implementation.

READ FULL TEXT
research
03/10/2021

Quantum machine learning with differential privacy

Quantum machine learning (QML) can complement the growing trend of using...
research
12/13/2022

Privacy-preserving Security Inference Towards Cloud-Edge Collaborative Using Differential Privacy

Cloud-edge collaborative inference approach splits deep neural networks ...
research
10/02/2020

GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning

Embedded systems demand on-device processing of data using Neural Networ...
research
02/07/2022

CECILIA: Comprehensive Secure Machine Learning Framework

Since machine learning algorithms have proven their success in data mini...
research
04/27/2022

Edge-PRUNE: Flexible Distributed Deep Learning Inference

Collaborative deep learning inference between low-resource endpoint devi...
research
05/26/2019

Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge

A wide variety of DNN applications increasingly rely on the cloud to per...
research
10/27/2022

Private and Reliable Neural Network Inference

Reliable neural networks (NNs) provide important inference-time reliabil...

Please sign up or login with your details

Forgot password? Click here to reset