Syft 0.5: A Platform for Universally Deployable Structured Transparency
This work addresses privacy concerns in machine learning deployments, but it appears incremental as it builds on existing privacy-enhancing technologies.
The paper tackles the problem of enabling privacy-preserving inference by proposing Syft 0.5, a framework that uses homomorphic encryption and split neural networks, resulting in significantly reduced computation time and payload size at the cost of model secrecy.
We present Syft 0.5, a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems. This framework is demonstrated through the design and implementation of a novel privacy-preserving inference information flow where we pass homomorphically encrypted activation signals through a split neural network for inference. We show that splitting the model further up the computation chain significantly reduces the computation time of inference and the payload size of activation signals at the cost of model secrecy. We evaluate our proposed flow with respect to its provision of the core structural transparency principles.