论文标题
深度四元建立特征的隐私保护功能
Deep Quaternion Features for Privacy Protection
论文作者
论文摘要
我们提出了一种修改神经网络的方法，以构建四个值的神经网络（QNN），以防止中间层特征泄漏输入信息。 QNN使用四个值值的特征，每个元素都是四个元素。 QNN将输入信息隐藏到四元成分特征的随机阶段。即使攻击者获得了网络参数和中间层特征，他们也无法在不知道目标阶段的情况下提取输入信息。这样，QNN可以有效地保护输入隐私。此外，与传统的神经网络相比，QNN的输出准确性仅会轻度降解，并且计算成本比其他保留隐私的方法要少得多。
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information. The QNN uses quaternion-valued features, where each element is a quaternion. The QNN hides input information into a random phase of quaternion-valued features. Even if attackers have obtained network parameters and intermediate-layer features, they cannot extract input information without knowing the target phase. In this way, the QNN can effectively protect the input privacy. Besides, the output accuracy of QNNs only degrades mildly compared to traditional neural networks, and the computational cost is much less than other privacy-preserving methods.
