通过抑制显示有关私有属性信息的功能来训练隐私保护视频分析管道
Training privacy-preserving video analytics pipelines by suppressing features that reveal information about private attributes
摘要：
深度神经网络越来越多地用于场景分析，包括评估人们对户外广告的注意力和反应。然而，由被训练成预测特定的、合意的属性（例如情感）的深度神经网络提取的特征也可以编码并因此揭示关于隐私的、受保护的属性（例如年龄或性别）的信息。在这项工作中，我们专注于这种泄漏的私人信息在推理时间。我们考虑一个对手访问的功能提取的层部署的神经网络，并使用这些功能来预测私人属性。为了防止这种攻击的成功，我们使用混淆损失来修改网络的训练，鼓励提取特征，使对手难以准确预测私有属性。我们使用公开的数据集在基于图像的任务上验证了这种训练方法。结果表明，与原始网络相比，所提出的PrivateNet可以将最先进的情感识别分类器的私人信息泄漏减少2.88%（性别）和13.06%（年龄组），对任务准确性的影响最小。
英文摘要：
Deep neural networks are increasingly deployed for scene analytics, including to evaluate the attention and reaction of people exposed to out-of-home advertisements. However, the features extracted by a deep neural network that was trained to predict a specific, consensual attribute (e.g. emotion) may also encode and thus reveal information about private, protected attributes (e.g. age or gender). In this work, we focus on such leakage of private information at inference time. We consider an adversary with access to the features extracted by the layers of a deployed neural network and use these features to predict private attributes. To prevent the success of such an attack, we modify the training of the network using a confusion loss that encourages the extraction of features that make it difficult for the adversary to accurately predict private attributes. We validate this training approach on image-based tasks using a publicly available dataset. Results show that, compared to the original network, the proposed PrivateNet can reduce the leakage of private information of a state-of-the-art emotion recognition classifier by 2.88% for gender and by 13.06% for age group, with a minimal effect on task accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
