DArL: Dynamic Parameter Adjustment for LWE-based Secure Inference
DArL: Dynamic Parameter Adjustment for LWE-based Secure Inference
复制标题
DOI：
10.23919/date.2019.8715110
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
S. Bian;Masayuki Hiromoto;Takashi Sato
中科院分区：
文献类型：
--
作者：
S. Bian;Masayuki Hiromoto;Takashi Sato
基于压缩加性同态加密（PAHE）的安全神经网络推理在应用密码学领域受到越来越多的关注。在这项工作中，我们试图提高基于LWE的安全推理的实用性，根据神经网络的底层架构动态地改变密码参数。首先，我们开发和应用理论方法来仔细研究安全推理的错误行为，并提出了一些参数，当使用较小的网络时，可以减少多达67%的密文大小。其次，我们使用基于sigma尺度采样方法的稀有事件模拟技术，以提供从（有点）任意分布中得出的累积误差大小的严格界限。最后，在实验中，我们实例化一个示例PAHE方案，并表明，我们可以进一步减少密文大小的3.3倍，如果我们采用一个二进制神经网络架构，沿着的计算加速比为2 - 3倍。
Packed additive homomorphic encryption (PAHE) based secure neural network inference is attracting increasing attention in the field of applied cryptography. In this work, we seek to improve the practicality of LWE-based secure inference by dynamically changing the cryptographic parameters depending on the underlying architecture of the neural network. First, we develop and apply theoretical methods to closely examine the error behavior of secure inference, and propose parameters that can reduce as much as 67% of ciphertext size when smaller networks are used. Second, we use rare-event simulation techniques based on the sigma-scale sampling method to provide tight bounds on the size of cumulative errors drawn from (somewhat) arbitrary distributions. Finally, in the experiment, we instantiate an example PAHE scheme and show that we can further reduce the ciphertext size by 3.3x if we adopt a binarized neural network architecture, along with a computation speedup of 2x–3x.