Prive-HD: Privacy-Preserved Hyperdimensional Computing
Prive-HD: Privacy-Preserved Hyperdimensional Computing
复制标题
DOI：
10.1109/dac18072.2020.9218493
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Behnam Khaleghi;M. Imani;Tajana Simunic
中科院分区：
文献类型：
--
作者：
Behnam Khaleghi;M. Imani;Tajana Simunic
数据的隐私性是机器学习中的一个主要挑战，因为经过训练的模型可能会暴露封闭数据集的敏感信息。此外，边缘设备有限的计算能力和容量使得云托管推理不可避免。将私人信息发送到远程服务器使得推断的隐私也容易受到攻击，因为易受影响的通信信道甚至不可信的主机。在本文中，我们的目标是保护隐私的训练和大脑启发的超维（HD）计算的推理，这是一种新的学习算法，由于其轻量级的计算和鲁棒性，特别是对具有严格约束的边缘设备的吸引力，因此越来越受到关注。事实上，尽管HD计算具有很好的属性，但由于其可逆计算，它几乎没有隐私。我们提出了一种准确性和隐私性的权衡方法，通过细致的量化和修剪超向量，HD的构建块，以实现差异化的私人模型，以及混淆发送的信息，用于云托管的推理。最后，我们将展示如何提出的技术也可以利用高效的硬件实现。
The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted inference inevitable. Sending private information to remote servers makes the privacy of inference also vulnerable because of susceptible communication channels or even untrustworthy hosts. In this paper, we target privacy-preserving training and inference of brain-inspired Hyperdimensional (HD) computing, a new learning algorithm that is gaining traction due to its light-weight computation and robustness particularly appealing for edge devices with tight constraints. Indeed, despite its promising attributes, HD computing has virtually no privacy due to its reversible computation. We present an accuracy-privacy trade-off method through meticulous quantization and pruning of hypervectors, the building blocks of HD, to realize a differentially private model as well as to obfuscate the information sent for cloud-hosted inference. Finally, we show how the proposed techniques can be also leveraged for efficient hardware implementation.