Cloud-based machine learning services (CMLS) enable organizations to take advantage of advanced models that are pre-trained on large quantities of data. The main shortcoming of using these services, however, is the difficulty of keeping the transmitted data private and secure. Asymmetric encryption requires the data to be decrypted in the cloud, while Homomorphic encryption is often too slow and difficult to implement. We propose One Way Scrambling by Deconvolution (OWSD), a deconvolution-based scrambling framework that offers the advantages of Homomorphic encryption at a fraction of the computational overhead. Extensive evaluation on multiple image datasets demonstrates OWSD's ability to achieve near-perfect classification performance when the output vector of the CMLS is sufficiently large. Additionally, we provide empirical analysis of the robustness of our approach.

翻译：以云为基础的机器学习服务使各组织能够利用在大量数据方面经过预先培训的先进模型(CMLS),但是,使用这些服务的主要缺点是难以保持传输的数据的隐私和安全。非对称加密要求将数据解密在云中,而单向加密往往过于缓慢和难以执行。我们提议由Deconvolution(OWSD)来拼凑单行道,这是一个以分流为基础的拼凑框架,在计算间接费用的一小部分上提供单向加密的好处。对多个图像数据集的广泛评价表明OWSD有能力在CMLS的产出矢量足够大的情况下实现接近完美的分类性能。此外,我们对我们的方法的稳健性进行了实证分析。