Secure multi-party computation (MPC) offers a practical foundation for privacy-preserving machine learning at the edge. However, current MPC systems rely heavily on communication and computation-intensive primitives-such as secure comparison for nonlinear inference, which are often impractical on resource-constrained platforms. To enable real-time inference under a resource-constrained platform, we introduce a Trusted Acceleration of Minimal-Interaction MPC framework, TAMI-MPC, for nonlinear evaluation. Specifically, we reduce communication cost by redesigning the core primitives, leaf comparison, and tree merge, reducing the interactive round from log(n) to just 1 per operation. Furthermore, unlike prior work that heavily relies on oblivious transfer (OT), a well-known computational bottleneck, we leverage synchronized seeds inside the TEE to eliminate OT for the vast majority of our designs, along with a correlated-randomness reuse technique that keeps new designs computationally lightweight. To fully realize the potential, we design a specialized accelerator that restructures the dataflow across stages to enable continuous, fine-grained streaming and high parallelism, reducing memory overhead. Our design achieves up to 4.86x speedup on ResNet-50 inference, compared with state-of-the-art CNN frameworks, and achieves up to 7.44x speedup on BERT-base inference, compared with state-of-the-art LLM frameworks.

翻译：安全多方计算（MPC）为边缘设备上的隐私保护机器学习提供了实用基础。然而，当前MPC系统严重依赖通信与计算密集型原语（如用于非线性推理的安全比较），这在资源受限平台上往往不切实际。为在资源受限平台上实现实时推理，我们提出了一种最小交互MPC的可信加速框架——TAMI-MPC，用于非线性评估。具体而言，我们通过重新设计核心原语（叶比较与树合并），将每次操作的交互轮数从log(n)降至1，从而降低通信成本。此外，与先前依赖遗忘传输（OT）这一已知计算瓶颈的工作不同，我们利用TEE内部的同步种子，在绝大多数设计中消除OT，并采用相关性随机数重用技术，使新设计保持计算轻量化。为充分释放潜力，我们设计了专用加速器，通过重构跨阶段数据流实现连续细粒度流式处理与高并行性，从而降低内存开销。与最先进的CNN框架相比，我们的设计在ResNet-50推理上实现最高4.86倍加速；与最先进的LLM框架相比，在BERT-base推理上实现最高7.44倍加速。