Privacy-Enhanced Training-as-a-Service for On-Device Intelligence: Concept, Architectural Scheme, and Open Problems

TL;DR

The paper tackles the challenge of privacy-preserving on-device AI training under data decentralization and device resource constraints. It introduces Privacy-Enhanced Training-as-a-Service (PTaaS), which outsources training to cloud or edge servers while devices submit anonymous one-shot queries, decoupling training from inference to reduce local burden. A five-layer PTaaS architecture is proposed, supported by enabling technologies such as privacy computing, cloud–edge collaboration, transfer learning, and information retrieval, plus a concrete process instantiation and a set of open problems. The work outlines security mechanisms, feasibility considerations, and a realistic assessment of privacy levels, highlighting potential practical impact while noting areas for further standardization and optimization.

Abstract

On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI inference without relying on remote servers. However, training models for on-device deployment face significant challenges due to the decentralized and privacy-sensitive nature of users' data, along with end-side constraints related to network connectivity, computation efficiency, etc. Existing training paradigms, such as cloud-based training, federated learning, and transfer learning, fail to sufficiently address these practical constraints that are prevalent for devices. To overcome these challenges, we propose Privacy-Enhanced Training-as-a-Service (PTaaS), a novel service computing paradigm that provides privacy-friendly, customized AI model training for end devices. PTaaS outsources the core training process to remote and powerful cloud or edge servers, efficiently developing customized on-device models based on uploaded anonymous queries, enhancing data privacy while reducing the computation load on individual devices. We explore the definition, goals, and design principles of PTaaS, alongside emerging technologies that support the PTaaS paradigm. An architectural scheme for PTaaS is also presented, followed by a series of open problems that set the stage for future research directions in the field of PTaaS.

Figures (4)

• Figure 1: Schematic diagram of PTaaS.
• Figure 2: Overview of the five-layer hierarchy structure of PTaaS.
• Figure 3: Framework of the instantiated PTaaS process based on cloud computing.
• Figure : Privacy-Enhanced Training-as-a-Service (PTaaS).