Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.24861 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911545134415872 |
|---|---|
| author | Li, Zhuoran Asl, Hanieh Totonchi Cai, Yifei Nouri, Ebrahim Zhao, Danella |
| author_facet | Li, Zhuoran Asl, Hanieh Totonchi Cai, Yifei Nouri, Ebrahim Zhao, Danella |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24861 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TAMI-MPC:Trusted Acceleration of Minimal-Interaction MPC for Efficient Nonlinear Inference Li, Zhuoran Asl, Hanieh Totonchi Cai, Yifei Nouri, Ebrahim Zhao, Danella Hardware Architecture 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. |
| title | TAMI-MPC:Trusted Acceleration of Minimal-Interaction MPC for Efficient Nonlinear Inference |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2603.24861 |