Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market. As deep learning tasks are mostly computation-intensive, it has become a trend to process raw data on devices and send the deep neural network (DNN) features to the cloud, where the features are further processed to return final results. However, there is always unexpected leakage with the release of features, with which an adversary could infer a significant amount of information about the original data. We propose a privacy-preserving reinforcement learning framework on top of the mobile cloud infrastructure from the perspective of DNN structures. The framework aims to learn a policy to modify the base DNNs to prevent information leakage while maintaining high inference accuracy. The policy can also be readily transferred to large-size DNNs to speed up learning. Extensive evaluations on a variety of DNNs have shown that our framework can successfully find privacy-preserving DNN structures to defend different privacy attacks.
翻译:由云层的机器学习服务驱动的众多学习驱动的移动应用程序在市场上越来越受欢迎。深层次学习任务大多是计算密集型的,因此它已成为一种趋势,即处理设备原始数据并将深神经网络特性传送到云层,而云层的特性则进一步处理,以返回最终结果。然而,随着特性的释放,总是会出现意外的泄漏,因此对手可以推断出关于原始数据的大量信息。我们提议从DNN结构的角度出发,在移动云层基础设施之上建立一个保护隐私的强化学习框架。该框架旨在学习一项政策,以修改基本 DNNP,防止信息泄漏,同时保持高的推断准确性。该政策还可以很容易地转移到大型DNNP,以加速学习。对各种DNP的大规模评价表明,我们的框架可以成功地找到保护隐私的DNN结构来保护不同的隐私攻击。