PAIGE: Towards a Hybrid-Edge Design for Privacy-Preserving Intelligent Personal Assistants


Intelligent Personal Assistants (IPAs) such as Apple’s Siri, Google Now, and Amazon Alexa are becoming an increasingly important class of web-service application. In contrast to keyword-oriented web search, IPAs provide a rich query interface that enables user interaction through images, audio, and natural language queries. However, supporting this interface involves compute-intensive machine-learning inference. To achieve acceptable performance, ML-driven IPAs increasingly depend on specialized hardware accelerators (eg GPUs, FPGAs or TPUs), increasing costs for IPA service providers. For end-users, IPAs also present considerable privacy risks given the sensitive nature of the data they capture. In this paper, we present Privacy Preserving Intelligent Personal Assistant at the EdGE (PAIGE), a hybrid edge-cloud architecture for privacy-preserving Intelligent Personal Assistants. PAIGE’s design is founded on the assumption that recent advances in low-cost hardware for machine-learning inference offer an opportunity to offload compute-intensive IPA ML tasks to the network edge. To allow privacy-preserving access to large IPA databases for less compute-intensive pre-processed queries, PAIGE leverages trusted execution environments at the server side. PAIGE’s hybrid design allows privacy-preserving hardware acceleration of compute-intensive tasks, while avoiding the need to move potentially large IPA question-answering databases to the edge. As a step towards realising PAIGE, we present a first systematic performance evaluation of existing edge accelerator hardware platforms for a subset of IPA workloads, and show they offer a competitive alternative to existing datacenter alternatives.

Proceedings of the 3rd International Workshop on Edge Systems, Analytics and Networking
Yilei Liang
Yilei Liang
Undergraduate Student, Working on Intelligent Personal Assistants at the Edge