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 2212.05428cs.CRcs.LG
收藏

ezDPS:一种高效的零知识机器学习推理流水线

ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline

Beijing Normal University(北京师范大学);Virginia Tech(弗吉尼亚理工大学)

Haodi Wang, Thang Hoang

摘要:

机器学习即服务(MLaaS)允许资源有限的客户端无处不在地访问强大的数据分析服务。尽管有其优点,但MLaaS对委托计算的完整性和服务器模型参数的隐私性提出了重大关注。为了解决这个问题,Zhang等人(CCS'20)发起了零知识机器学习(zkML)的研究。之后很少有人提出zkML方案;然而,它们专注于单一的ML分类算法,这些算法可能无法提供令人满意的准确性或需要大规模训练数据和模型参数,这对于某些应用来说可能是不可取的。我们提出了ezDPS,一个新的高效和零知识ML推理方案。与以前的作品不同,ezDPS是一个zkML管道,其中数据在多个阶段进行处理,以获得高精度。ezDPS的每个阶段都利用了一个已建立的ML算法,该算法在各种应用中都是有效的,包括离散小波变换,主成分分析和支持向量机。我们设计新的小工具来有效地证明ML操作。我们完全实现了ezDPS,并在真实数据集上评估了其性能。实验结果表明,ezDPS在所有指标上比基于通用电路的方法效率高一到三个数量级,同时保持比单一ML分类方法更理想的准确性。

英文摘要:

Machine Learning as a service (MLaaS) permits resource-limited clients to access powerful data analytics services ubiquitously. Despite its merits, MLaaS poses significant concerns regarding the integrity of delegated computation and the privacy of the server's model parameters. To address this issue, Zhang et al. (CCS'20) initiated the study of zero-knowledge Machine Learning (zkML). Few zkML schemes have been proposed afterward; however, they focus on sole ML classification algorithms that may not offer satisfactory accuracy or require large-scale training data and model parameters, which may not be desirable for some applications. We propose ezDPS, a new efficient and zero-knowledge ML inference scheme. Unlike prior works, ezDPS is a zkML pipeline in which the data is processed in multiple stages for high accuracy. Each stage of ezDPS is harnessed with an established ML algorithm that is shown to be effective in various applications, including Discrete Wavelet Transformation, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove ML operations effectively. We fully implemented ezDPS and assessed its performance on real datasets. Experimental results showed that ezDPS achieves one-to-three orders of magnitude more efficient than the generic circuit-based approach in all metrics while maintaining more desirable accuracy than single ML classification approaches.

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。

↑