DisguisedNets: Secure Image Outsourcing for Confidential Model Training in Clouds

Abstract

Large training data and expensive model tweaking are standard features of deep learning with images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which also raises privacy concerns. Existing cryptographic solutions for training deep neural networks (DNNs) are too expensive, cannot effectively utilize cloud GPU resources, and also put a significant burden on client-side pre-processing. This paper presents an image disguising approach: DisguisedNets that allows users to securely outsource images to the cloud and enables confidential, efficient GPU-based model training. DisgisedNets use a novel combination of image blocktization, block-level random permutation, and block-level secure transformations: random multidimensional projection (RMT) or AES pixel-level encryption (AES) to transform training data. Users can use existing DNN training methods and GPU resources without any modification to training models with disguised images. We have analyzed and evaluated the methods under a multi-level threat model and compared them with another similar method – InstaHide. We also show that the image disguising approach, including both DisguisedNets and InstaHide, can effectively protect models from model-targeted attacks.