While it is encouraging to witness the recent development in privacy-preserving Machine Learning as a Service (MLaaS), there still exists a significant performance gap for its deployment in real-world applications. We observe the state-of-the-art frameworks follow a compute-and-share principle for every function output where the summing in linear functions, which is the last of two steps for function output, involves all rotations (which is the most expensive HE operation), and the multiplexing in nonlinear functions, which is also the last of two steps for function output, introduces noticeable communication rounds. Therefore, we challenge the conventional compute-and-share logic and introduce the first joint linear and nonlinear computation across functions that features by 1) the PHE triplet for computing the nonlinear function, with which the multiplexing is eliminated; 2) the matrix encoding to calculate the linear function, with which all rotations for summing is removed; and 3) the network adaptation to reassemble the model structure, with which the joint computation module is utilized as much as possible. The boosted efficiency is verified by the numerical complexity, and the experiments demonstrate up to 13x speedup for various functions used in the state-of-the-art models and up to 5x speedup over mainstream neural networks.
翻译:令人欣慰的是,人们目睹了隐私保存机学习服务(MLaaS)的最近发展,但是,在实际应用中,仍然存在着显著的绩效差距。我们观察到,最先进的框架遵循每个函数输出的计算和分享原则,即线性函数的缩放是函数输出的两个步骤中的最后一个,涉及所有旋转(这是最昂贵的HE操作),以及非线性函数的多重x化,这也是功能输出的两个步骤的最后两个步骤,引入了显著的通信回合。因此,我们质疑常规的计算和分享逻辑,并引入了第一个对功能的在线和非线性联合计算,其特点为:1) PHE 三进制用于计算非线性函数的计算,从而消除多重xx;2)用于计算线性函数的矩阵编码,从而删除所有调音的所有旋转;3)网络调整,以重新评估模型结构,并尽可能使用联合计算模块。因此,通过数字复杂性验证了提高的效率,并引入了第一个联合线性和非线性计算方法,1)用于计算非线性函数,从而消除多重x;2)用来计算的所有线性功能;3 用于各种速度的模型。在5x上使用的实验中,用于各种速度。