# Privacy-preserving Sensory Data Recovery

## TL;DR

This paper introduces PPCS-MAA, a novel privacy-preserving sensory data recovery method that maintains high accuracy by leveraging multi-attribute correlations and homomorphic encryption, addressing privacy concerns in sensor networks.

## Contribution

It proposes a new combined scheme of privacy-preserving compressive sensing with multi-attribute assistance, enhancing data recovery accuracy while ensuring privacy in sensor networks.

## Key findings

- Outperforms existing solutions in real data simulations
- Effectively encrypts data without losing accuracy
- Leverages multi-attribute correlations for better recovery

## Abstract

In recent years, a large scale of various wireless sensor networks have been deployed for basic scientific works. Massive data loss is so common that there is a great demand for data recovery. While data recovery methods fulfil the requirement of accuracy, the potential privacy leakage caused by them concerns us a lot. Thus the major challenge of sensory data recovery is the issue of effective privacy preservation. Existing algorithms can either accomplish accurate data recovery or solve privacy issue, yet no single design is able to address these two problems simultaneously. Therefore in this paper, we propose a novel approach Privacy-Preserving Compressive Sensing with Multi-Attribute Assistance (PPCS-MAA). It applies PPCS scheme to sensory data recovery, which can effectively encrypts sensory data without decreasing accuracy, because it maintains the homomorphic obfuscation property for compressive sensing. In addition, multiple environmental attributes from sensory datasets usually have strong correlation so that we design a MultiAttribute Assistance (MAA) component to leverage this feature for better recovery accuracy. Combining PPCS with MAA, the novel recovery scheme can provide reliable privacy with high accuracy. Firstly, based on two real datasets, IntelLab and GreenOrbs, we reveal the inherited low-rank features as the ground truth and find such multi-attribute correlation. Secondly, we develop a PPCS-MAA algorithm to preserve privacy and optimize the recovery accuracy. Thirdly, the results of real data-driven simulations show that the algorithm outperforms the existing solutions.