当前位置: X-MOL 学术IEEE Trans. Parallel Distrib. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Service
IEEE Transactions on Parallel and Distributed Systems ( IF 5.6 ) Pub Date : 2021-03-23 , DOI: 10.1109/tpds.2021.3068195
Lingchen Zhao , Qian Wang , Cong Wang , Qi Li , Chao Shen , Bo Feng

Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS solutions still lack strong assurances on: 1) service correctness (i.e., whether the MLaaS works as expected); 2) trustworthy accounting (i.e., whether the bill for the MLaaS resource consumption is correctly accounted); 3) fair payment (i.e., whether a client gets the entire MLaaS result before making the payment). Without these assurances, unfaithful service providers can return improperly-executed ML task results or partially-trained ML models while asking for over-claimed rewards. Moreover, it is hard to argue for wide adoption of MLaaS to both the client and the service provider, especially in the open market without a trusted third party. In this article, we present VeriML, a novel and efficient framework to bring integrity assurances and fair payments to MLaaS. With VeriML, clients can be assured that ML tasks are correctly executed on an untrusted server, and the resource consumption claimed by the service provider equals to the actual workload. We strategically use succinct non-interactive arguments of knowledge (SNARK) on randomly-selected iterations during the ML training phase for efficiency with tunable probabilistic assurance. We also develop multiple ML-specific optimizations to the arithmetic circuit required by SNARK. Our system implements six common algorithms: linear regression, logistic regression, neural network, support vector machine, K-means and decision tree. The experimental results have validated the practical performance of VeriML.

中文翻译:


VeriML:为机器学习即服务提供完整性保证和公平支付



机器学习即服务 (MLaaS) 允许资源有限的客户将昂贵的 ML 任务外包给功能强大的服务器。尽管带来了巨大的好处,但当前的MLaaS解决方案仍然缺乏对以下方面的有力保证:1)服务正确性(即MLaaS是否按预期工作); 2)可信记账(即MLaaS资源消耗的账单是否正确记账); 3)公平支付(即客户在支付之前是否获得完整的MLaaS结果)。如果没有这些保证,不忠实的服务提供商可能会返回未正确执行的 ML 任务结果或部分训练的 ML 模型,同时索取过高的奖励。此外,很难主张客户和服务提供商都广泛采用 MLaaS,尤其是在没有可信第三方的开放市场中。在本文中,我们介绍了 VeriML,这是一种新颖且高效的框架,可为 MLaaS 带来完整性保证和公平支付。借助 VeriML,客户可以确信 ML 任务在不受信任的服务器上正确执行,并且服务提供商声称的资源消耗等于实际工作负载。我们在 ML 训练阶段在随机选择的迭代中策略性地使用简洁的非交互式知识论证 (SNARK),以提高效率并提供可调的概率保证。我们还针对 SNARK 所需的算术电路开发了多项针对 ML 的优化。我们的系统实现了六种常见算法:线性回归、逻辑回归、神经网络、支持向量机、K-means 和决策树。实验结果验证了VeriML的实用性能。
更新日期:2021-03-23
down
wechat
bug