Efficient Data Perturbation for Privacy Preserving and Accurate Data Stream Mining

TL;DR

This paper introduces $P^2RoCAl$, an efficient data stream perturbation method that balances privacy and utility, achieving high classification accuracy and resistance to reconstruction attacks in IoT data streams.

Contribution

The paper presents $P^2RoCAl$, a novel data perturbation technique that improves utility and privacy in IoT data stream mining compared to existing methods.

Findings

Classification accuracy close to original data streams.

Higher resilience against data reconstruction attacks.

Efficient and scalable for IoT applications.

Abstract

The widespread use of the Internet of Things (IoT) has raised many concerns, including the protection of private information. Existing privacy preservation methods cannot provide a good balance between data utility and privacy, and also have problems with efficiency and scalability. This paper proposes an efficient data stream perturbation method (named as $P^2RoCAl$). $P^2RoCAl$ offers better data utility than similar methods: classification accuracies of $P^2RoCAl$ perturbed data streams are very close to those of the original data streams. $P^2RoCAl$ also provides higher resilience against data reconstruction attacks.