Privacy-Preserving Feature Coding for Machines
This addresses privacy concerns in automated machine vision pipelines, though it is incremental as it builds on existing adversarial training and autoencoder methods.
The paper tackles the problem of preserving privacy in machine vision by removing private information from images without significantly affecting task accuracy, achieving a 0.8 dB reduction in input reconstruction ability and 30% bit savings.
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% bit savings are achieved compared to coding the features directly.