PrivEdge: From Local to Distributed Private Training and Prediction

04/12/2020
by   Ali Shahin Shamsabadi, et al.
0

Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-of-the-art centralised architectures on three privacy-sensitive image-based tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data. The source code is available at https://github.com/smartcameras/PrivEdge.

READ FULL TEXT

page 1

page 9

page 11

page 12

research
10/25/2019

Distributed Privacy-Preserving Prediction

In privacy-preserving machine learning, individual parties are reluctant...
research
07/05/2018

Privacy-preserving Machine Learning through Data Obfuscation

As machine learning becomes a practice and commodity, numerous cloud-bas...
research
02/10/2018

Distributed One-class Learning

We propose a cloud-based filter trained to block third parties from uplo...
research
06/17/2022

CLEAR: A Fully User-side Image Search System

We use many search engines on the Internet in our daily lives. However, ...
research
02/09/2018

Deep Private-Feature Extraction

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep mo...
research
05/11/2018

Under the Underground: Predicting Private Interactions in Underground Forums

Underground forums where users discuss, buy, and sell illicit services a...
research
08/24/2022

On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks

In spite of the legal advances in personal data protection, the issue of...

Please sign up or login with your details

Forgot password? Click here to reset