Privacy-Preserving Deep Inference for Rich User Data on The Cloud
This addresses privacy concerns for users of cloud-based AI services, though it is incremental as it builds on existing edge processing and fine-tuning techniques.
The paper tackles the problem of privacy risks in cloud-based deep inference on rich user data by proposing a hybrid approach that breaks down and fine-tunes large models for cooperative processing, achieving a significant reduction in information exposure to unintended cloud tasks with minimal processing costs.
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator can perform secondary inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a hybrid approach for breaking down large, complex deep models for cooperative, privacy-preserving analytics. We do this by breaking down the popular deep architectures and fine-tune them in a particular way. We then evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also asses the local inference cost of different layers on a modern handset for mobile applications. Our evaluations show that by using certain kind of fine-tuning and embedding techniques and at a small processing costs, we can greatly reduce the level of information available to unintended tasks applied to the data feature on the cloud, and hence achieving the desired tradeoff between privacy and performance.