当前位置:
X-MOL 学术
›
arXiv.cs.CR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks
arXiv - CS - Cryptography and Security Pub Date : 2021-05-05 , DOI: arxiv-2105.01827 Qiao Zhang, Chunsheng Xin, Hongyi Wu
arXiv - CS - Cryptography and Security Pub Date : 2021-05-05 , DOI: arxiv-2105.01827 Qiao Zhang, Chunsheng Xin, Hongyi Wu
Machine Learning as a Service (MLaaS) is enabling a wide range of smart
applications on end devices. However, privacy-preserved computation is still
expensive. Our investigation has found that the most time-consuming component
of the HE-based linear computation is a series of Permutation (Perm) operations
that are imperative for dot product and convolution in privacy-preserved MLaaS.
To this end, we propose GALA: Greedy computAtion for Linear Algebra in
privacy-preserved neural networks, which views the HE-based linear computation
as a series of Homomorphic Add, Mult and Perm operations and chooses the least
expensive operation in each linear computation step to reduce the overall cost.
GALA makes the following contributions: (1) It introduces a row-wise weight
matrix encoding and combines the share generation that is needed for the
GC-based nonlinear computation, to reduce the Perm operations for the dot
product; (2) It designs a first-Add-second-Perm approach (named kernel
grouping) to reduce Perm operations for convolution. As such, GALA efficiently
reduces the cost for the HE-based linear computation, which is a critical
building block in almost all of the recent frameworks for privacy-preserved
neural networks, including GAZELLE (Usenix Security'18), DELPHI (Usenix
Security'20), and CrypTFlow2 (CCS'20). With its deep optimization of the
HE-based linear computation, GALA can be a plug-and-play module integrated into
these systems to further boost their efficiency. Our experiments show that it
achieves a significant speedup up to 700x for the dot product and 14x for the
convolution computation under different data dimensions. Meanwhile, GALA
demonstrates an encouraging runtime boost by 2.5x, 2.7x, 3.2x, 8.3x, 7.7x, and
7.5x over GAZELLE and 6.5x, 6x, 5.7x, 4.5x, 4.2x, and 4.1x over CrypTFlow2, on
AlexNet, VGG, ResNet-18, ResNet-50, ResNet-101, and ResNet-152, respectively.
中文翻译:
GALA:隐私保护神经网络中线性代数的贪婪计算
机器学习即服务(MLaaS)正在终端设备上启用各种智能应用程序。但是,保留隐私的计算仍然很昂贵。我们的研究发现,基于HE的线性计算中最耗时的部分是一系列置换(Perm)操作,这些操作对于保留隐私的MLaaS中的点积和卷积是必不可少的。为此,我们提出了GALA:隐私保护神经网络中线性代数的贪婪计算,该算法将基于HE的线性计算视为一系列同态加,多和彼尔姆运算,并在每个线性计算步骤中选择成本最低的运算降低整体成本。GALA做出以下贡献:(1)引入了行权矩阵编码,并结合了基于GC的非线性计算所需的份额生成,以减少点积的Perm运算;(2)设计了第一种Add-second-Perm方法(称为内核分组)以减少用于卷积的Perm操作。因此,GALA有效地降低了基于HE的线性计算的成本,这几乎是所有最近的所有隐私保护神经网络框架的重要组成部分,其中包括GAZELLE(Usenix Security'18),DELPHI(Usenix Security' 20)和CrypTFlow2(CCS'20)。通过对基于HE的线性计算进行深度优化,GALA可以作为即插即用模块集成到这些系统中,以进一步提高其效率。我们的实验表明,在不同数据尺寸下,点积和卷积计算的速度都可以明显提高到700倍和14倍。同时,GALA展示了令人鼓舞的运行时性能,与GAZELLE相比提高了2.5倍,2.7倍,3.2倍,8.3倍,7.7倍和7.5倍,与CrypTFlow2相比分别提高了6.5倍,6倍,5.7倍,4.5倍,4.2倍和4.1倍,分别在AlexNet,VGG,ResNet-18,ResNet-50,ResNet-101和ResNet-152上运行。
更新日期:2021-05-06
中文翻译:
GALA:隐私保护神经网络中线性代数的贪婪计算
机器学习即服务(MLaaS)正在终端设备上启用各种智能应用程序。但是,保留隐私的计算仍然很昂贵。我们的研究发现,基于HE的线性计算中最耗时的部分是一系列置换(Perm)操作,这些操作对于保留隐私的MLaaS中的点积和卷积是必不可少的。为此,我们提出了GALA:隐私保护神经网络中线性代数的贪婪计算,该算法将基于HE的线性计算视为一系列同态加,多和彼尔姆运算,并在每个线性计算步骤中选择成本最低的运算降低整体成本。GALA做出以下贡献:(1)引入了行权矩阵编码,并结合了基于GC的非线性计算所需的份额生成,以减少点积的Perm运算;(2)设计了第一种Add-second-Perm方法(称为内核分组)以减少用于卷积的Perm操作。因此,GALA有效地降低了基于HE的线性计算的成本,这几乎是所有最近的所有隐私保护神经网络框架的重要组成部分,其中包括GAZELLE(Usenix Security'18),DELPHI(Usenix Security' 20)和CrypTFlow2(CCS'20)。通过对基于HE的线性计算进行深度优化,GALA可以作为即插即用模块集成到这些系统中,以进一步提高其效率。我们的实验表明,在不同数据尺寸下,点积和卷积计算的速度都可以明显提高到700倍和14倍。同时,GALA展示了令人鼓舞的运行时性能,与GAZELLE相比提高了2.5倍,2.7倍,3.2倍,8.3倍,7.7倍和7.5倍,与CrypTFlow2相比分别提高了6.5倍,6倍,5.7倍,4.5倍,4.2倍和4.1倍,分别在AlexNet,VGG,ResNet-18,ResNet-50,ResNet-101和ResNet-152上运行。