In this paper, we propose a general framework to provide a desirable trade-off between inference accuracy and privacy protection in the inference as service scenario (IAS). Instead of sending data directly to the server, the user will preprocess the data through a privacy-preserving mapping, which will increase privacy protection but reduce inference accuracy. To properly address the trade-off between privacy protection and inference accuracy, we formulate an optimization problem to find the privacy-preserving mapping. Even though the problem is non-convex in general, we characterize nice structures of the problem and develop an iterative algorithm to find the desired privacy-preserving mapping, with convergence analysis provided under certain assumptions. From numerical examples, we observe that the proposed method has better performance than gradient ascent method in the convergence speed, solution quality and algorithm stability.

中文翻译：

---

推理即服务的最佳准确性与隐私权衡


在本文中，我们提出了一个通用框架，以在推理即服务场景（IAS）中提供推理准确性和隐私保护之间的理想权衡。用户不会直接将数据发送到服务器，而是通过隐私保护映射对数据进行预处理，这会增加隐私保护，但会降低推理准确性。为了正确解决隐私保护和推理准确性之间的权衡，我们制定了一个优化问题来找到隐私保护映射。尽管问题通常是非凸的，但我们描述了问题的良好结构，并开发了一种迭代算法来找到所需的隐私保护映射，并在某些假设下提供收敛分析。从数值算例中我们观察到该方法在收敛速度、解质量和算法稳定性方面均优于梯度上升法。