论文标题
机器的隐私功能编码
Privacy-Preserving Feature Coding for Machines
论文作者
论文摘要
自动化的机器视觉管道不需要确切的视觉内容来执行其任务。因此，有可能从数据中删除私人信息而不会显着影响机器视觉准确性。我们提出了一种新颖的方法，以创建一个图像的隐私潜在表示，该图像可以由下游机器视觉模型使用。这种潜在表示是使用对抗训练来构建的，以防止在保留任务准确性的同时准确重建输入。具体而言，我们分割了一个深神经网络（DNN）模型，并插入一个自动编码器，其目的是降低维度，并删除与输入重建相关的信息，同时最大程度地减少对任务准确性的影响。我们的结果表明，在同等任务准确性下，输入重建能力可以降低约0.8 dB，而降级集中在边缘附近，这对于隐私很重要。同时，与直接编码功能相比，可节省30％的位。
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.
