arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.08012cs.LGcs.CR
收藏

AutoFHE:面向FHE高效评估的CNN自动适配

AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE

Michigan State University(密歇根州立大学)

Wei Ao, Vishnu Naresh Boddeti

AI总结:

AutoFHE自动适配CNN用于RNS-CKKS安全推理,采用逐层混合次数多项式激活函数并联合优化自举放置,在多目标框架下平衡精度与延迟,显著加速并提升精度。

摘要:

在RNS-CKKS下对深度卷积神经网络(CNN)进行安全推理涉及对不支持的非线性激活函数的多项式近似。然而,现有方法存在三个主要局限性:1)不灵活性:多项式近似及相关的同态评估架构是针对每个CNN架构手动定制的,不能推广到其他网络。2)次优近似:每个激活函数被单独近似,而非对CNN所表示的函数进行整体近似。3)受限设计:要么使用高次多项式近似,要么使用低次多项式近似。前者保持高精度,但因自举操作而减慢推理速度;后者加速密文推理,但牺牲精度。为解决这些局限性,我们提出AutoFHE,它自动适配标准CNN以在RNS-CKKS下进行安全推理。关键思想是采用逐层混合次数的多项式激活函数,并与同态评估架构在自举操作放置方面进行联合优化。该问题被建模为多目标优化框架,以最大化精度并最小化自举操作数量。AutoFHE可灵活应用于任何CNN架构,并提供跨越精度与延迟权衡的多种解决方案。在RNS-CKKS加密的CIFAR数据集上的实验评估表明,与采用高次多项式的方法相比,AutoFHE将安全推理加速了1.32倍至1.8倍。与使用低次多项式的方法相比,它还将精度提高了最多2.56%。最后,与TFHE下的CNN相比,AutoFHE分别将推理速度提高了103倍,精度提高了3.46%。

英文摘要:

Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves polynomial approximation of unsupported non-linear activation functions. However, existing approaches have three main limitations: 1) Inflexibility: The polynomial approximation and associated homomorphic evaluation architecture are customized manually for each CNN architecture and do not generalize to other networks. 2) Suboptimal Approximation: Each activation function is approximated instead of the function represented by the CNN. 3) Restricted Design: Either high-degree or low-degree polynomial approximations are used. The former retains high accuracy but slows down inference due to bootstrapping operations, while the latter accelerates ciphertext inference but compromises accuracy. To address these limitations, we present AutoFHE, which automatically adapts standard CNNs for secure inference under RNS-CKKS. The key idea is to adopt layerwise mixed-degree polynomial activation functions, which are optimized jointly with the homomorphic evaluation architecture in terms of the placement of bootstrapping operations. The problem is modeled within a multi-objective optimization framework to maximize accuracy and minimize the number of bootstrapping operations. AutoFHE can be applied flexibly on any CNN architecture, and it provides diverse solutions that span the trade-off between accuracy and latency. Experimental evaluation over RNS-CKKS encrypted CIFAR datasets shows that AutoFHE accelerates secure inference by $1.32\times$ to $1.8\times$ compared to methods employing high-degree polynomials. It also improves accuracy by up to 2.56% compared to methods using low-degree polynomials. Lastly, AutoFHE accelerates inference and improves accuracy by $103\times$ and 3.46%, respectively, compared to CNNs under TFHE.

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。

↑