FFConv：加密数据的快速分解卷积神经网络推理
FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data
摘要：
同态加密（HE）允许对加密数据（密文）进行计算而无需首先对其进行解密，从而为云中的隐私保护应用程序提供安全但速度非常慢的卷积神经网络（CNN）推理。为了减少推理延迟，一种方法是将多个消息打包到单个密文中，以便减少密文的数量并支持密文之间的同态乘法累加（HMA）操作的大规模并行性。尽管HECNN推理速度更快，但主流打包方案密集打包（DensePack）和卷积打包（ConvPack）引入了昂贵的旋转开销，这降低了HECNN用于更深和更宽的CNN架构的推理延迟。在本文中，我们提出了一种低秩分解方法FFConv专用于有效的密文包装，以减少旋转开销和HMA操作。FFConv使用低秩分解卷积来近似d x d卷积层，其中具有较少通道的d x d低秩卷积之后是1 x 1卷积以恢复通道。使用DensePack的d x d低秩卷积显著减少了旋转操作，而使用ConvPack的1 x 1卷积的旋转开销接近于零。据我们所知，FFConv是第一个能够同时减少DensePack和ConvPack所产生的旋转开销的工作，而不会向HECNN推理管道中引入额外的特殊块。与现有技术的LoLa和Falcon相比，我们的方法分别将推理延迟降低了88%和21%，并且在MNIST和CIFAR-10上具有相当的准确性。
英文摘要：
Homomorphic Encryption (HE), allowing computations on encrypted data (ciphertext) without decrypting it first, enables secure but prohibitively slow Convolutional Neural Network (CNN) inference for privacy-preserving applications in clouds. To reduce the inference latency, one approach is to pack multiple messages into a single ciphertext in order to reduce the number of ciphertexts and support massive parallelism of Homomorphic Multiply-Accumulate (HMA) operations between ciphertexts. Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures. In this paper, we propose a low-rank factorization method named FFConv dedicated to efficient ciphertext packing for reducing both the rotation overhead and HMA operations. FFConv approximates a d x d convolution layer with low-rank factorized convolutions, in which a d x d low-rank convolution with fewer channels is followed by a 1 x 1 convolution to restore the channels. The d x d low-rank convolution with DensePack leads to significantly reduced rotation operations, while the rotation overhead of 1 x 1 convolution with ConvPack is close to zero. To our knowledge, FFConv is the first work that is capable of reducing the rotation overhead incurred by DensePack and ConvPack simultaneously, without introducing additional special blocks into the HECNN inference pipeline. Compared to prior art LoLa and Falcon, our method reduces the inference latency by up to 88% and 21%, respectively, with comparable accuracy on MNIST and CIFAR-10.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
