A Machine Learning Framework for Privacy-Aware Distributed Functional Compression over AWGN Channels
A Machine Learning Framework for Privacy-Aware Distributed Functional Compression over AWGN Channels
复制标题
DOI：
10.1109/itw54588.2022.9965919
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Yashas Malur Saidutta;F. Fekri;A. Abdi
中科院分区：
文献类型：
--
作者：
Yashas Malur Saidutta;F. Fekri;A. Abdi
在许多不同的领域，分布式物联网设备通过与边缘路由器通信来执行协作推理。通常，感觉数据包含不应泄露给路由器的敏感属性。为了解决这个问题，据我们所知，我们开发了第一个隐私感知的机器学习框架，用于AWGN通道上的分布式功能压缩。我们隐私保护方法的关键特征是，我们只关注数据的敏感属性，而不是支付高昂的成本来保护一切。利用基于互信息的隐私约束，我们首先提出了一种新的近似上界来保护感知数据压缩表示中的敏感属性。接下来，结合上界，我们提出了对抗性下界，以进一步加强保护。第三，我们对这些界限提出了新的分解，这样的分布式边缘设备可以通过独立地对其组件进行私有化来确保总体隐私。这使我们能够提出一种增强的隐私感知算法，在训练和推理过程中保护敏感信息。我们的实验表明，我们提出的方法在隐私和效用之间的权衡明显好于现有的机制。
In many diverse fields, distributed IoT devices perform collaborative inference by communicating with an edge router. Often sensory data contains sensitive attributes that should not be revealed to the router. To address this, we develop, to the best of our knowledge, the first privacy-aware machine learning framework for distributed functional compression over AWGN channels. The key feature of our approach to privacy is that we focus only on sensitive attributes of data rather than paying a high cost to protect everything. Employing a mutual information based privacy constraint, we first propose a novel approximate upper bound to protect sensitive attributes in the compressed representations of the sensory data. Next, in conjunction with the upper bound, we propose an adversarial lower bound to enhance the protection further. Thirdly, we propose novel decompositions to these bounds such distributed edge devices can ensure overall privacy by independently privatizing their components. This allows us to propose an enhanced privacy-aware algorithm that protects sensitive information during training and inference. Our experiments show that the privacy-utility trade-off from our proposed methods is significantly better than existing mechanisms.