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.
翻译:自动机视管道不需要精确的视觉内容来执行任务。 因此, 有可能在不严重影响机器视觉准确性的情况下从数据中去除私人信息。 我们展示了一种创新的方法, 来创建一种可以被下游机视像模型使用的图像的隐私保护潜在代表形式。 这种潜在代表形式是使用对抗性培训来构建的, 以防止在保持任务准确性的同时准确重建输入。 具体地说, 我们拆分一个深神经网络模型, 并插入一个自动编码器, 其目的是既减少维度, 也删除与输入重建有关的信息, 同时又尽量减少对任务准确性的影响。 我们的结果显示, 投入重建能力可以降低大约0. 8 dB 的类似准确性, 其降解集中在边缘, 这对隐私很重要 。 与此同时, 与直接编码特征相比, 节省了 30% 。