Privacy-Preserving Feature Coding for Machines

10/03/2022
by   Bardia Azizian, et al.
0

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We present a novel method to create a privacy-preserving latent representation of an image that could be used by a downstream machine vision model. This latent representation is constructed using adversarial training to prevent accurate reconstruction of the input while preserving the task accuracy. Specifically, we split a Deep Neural Network (DNN) model and insert an autoencoder whose purpose is to both reduce the dimensionality as well as remove information relevant to input reconstruction while minimizing the impact on task accuracy. Our results show that input reconstruction ability can be reduced by about 0.8 dB at the equivalent task accuracy, with degradation concentrated near the edges, which is important for privacy. At the same time, 30

READ FULL TEXT
research
07/23/2018

2P-DNN : Privacy-Preserving Deep Neural Networks Based on Homomorphic Cryptosystem

Machine Learning as a Service (MLaaS), such as Microsoft Azure, Amazon A...
research
11/22/2019

Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

Data privacy has emerged as an important issue as data-driven deep learn...
research
11/10/2022

Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings

Privacy-preserving machine learning in data-sharing processes is an ever...
research
06/11/2020

Privacy-Preserving Visual Feature Descriptors through Adversarial Affine Subspace Embedding

Many computer vision systems require users to upload image features to t...
research
07/22/2018

Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study

This paper aims to improve privacy-preserving visual recognition, an inc...
research
02/14/2018

Learning Privacy Preserving Encodings through Adversarial Training

We present a framework to learn privacy-preserving encodings of images (...
research
04/19/2023

Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks

Split learning of deep neural networks (SplitNN) has provided a promisin...

Please sign up or login with your details

Forgot password? Click here to reset