Spin: An Efficient Secure Computation Framework with GPU Acceleration

2024-02-04 · Wuxuan Jiang, Xiangjun Song, Shenbai Hong, Haijun Zhang, Wenxin Liu, Bo Zhao, Wei Xu, Yi Li

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized protocols for non-linear functions that are critical for machine learning, as well as several novel optimizations specific to attention that is the fundamental unit of Transformer models, allowing Spin to perform non-trivial CNNs training and Transformer inference without sacrificing security. At the backend level, Spin leverages GPU, CPU, and RDMA-enabled smart network cards for acceleration. Comprehensive evaluations demonstrate that Spin can be up to $2\times$ faster than the state-of-the-art for deep neural network training. For inference on a Transformer model with 18.9 million parameters, our attention-specific optimizations enable Spin to achieve better efficiency, less communication, and better accuracy.

📄 PDF Abstract BibTeX arXiv:2402.02320

Code (0)

등록된 구현이 없습니다.

Tasks

CPUGPU

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Multi-Head Attention 설명 없음

Adam 설명 없음

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Internal sensory models allow for balance control using muscle spindle acceleration feedback

2024-03-01 · Eric Maris

Motor control requires sensory feedback, and the nature of this feedback has implications for the tasks of the central nervous system (CNS): for an approximately linear mechanical system (e.g., a freely standing person, …

SecONNds: Secure Outsourced Neural Network Inference on ImageNet

2025-06-13 · Shashank Balla

The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving soluti…

CPU GPU Privacy Preserving

PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference

2022-09-20 · Hongwu Peng, Shanglin Zhou, Yukui Luo, Shijin Duan 외

The rapid growth and deployment of deep learning (DL) has witnessed emerging privacy and security concerns. To mitigate these issues, secure multi-party computation (MPC) has been discussed, to enable the privacy-preserv…

Neural Architecture Search Privacy Preserving

SPARX: Secure and Privacy-Aware Approximate CNN Acceleration with Edge RISC-V SoC

2026-06-08 · Sonu Kumar, Akash Sankhe, Mukul Lokhande, Santosh Kumar Vishvakarma arxiv

Edge-AI systems increasingly require real-time CNN inference under strict energy, performance, security, and privacy constraints. Approximate computing improves hardware efficiency by exploiting the error resilience of n…

ENSI: Efficient Non-Interactive Secure Inference for Large Language Models

2025-09-11 · Zhiyu He, Maojiang Wang, Xinwen Gao, Yuchuan Luo 외 arxiv

Secure inference enables privacy-preserving machine learning by leveraging cryptographic protocols that support computations on sensitive user data without exposing it. However, integrating cryptographic protocols with l…