PriMaL: A Privacy-Preserving Machine Learning Method for Event Detection in Distributed Sensor Networks

TL;DR

PriMaL is a novel privacy-preserving machine learning layer that enhances privacy in distributed sensor networks for event detection without sacrificing detection accuracy, demonstrated through simulations across various network configurations.

Contribution

Introduces PriMaL, a machine learning layer that reduces privacy costs in distributed event detection, maintaining performance comparable to centralized algorithms.

Findings

PriMaL reduces privacy footprint below centralized methods.

Distributed detection performance remains statistically comparable to centralized methods.

Effective across multiple network topologies and parameters.

Abstract

This paper introduces PriMaL, a general PRIvacy-preserving MAchine-Learning method for reducing the privacy cost of information transmitted through a network. Distributed sensor networks are often used for automated classification and detection of abnormal events in high-stakes situations, e.g. fire in buildings, earthquakes, or crowd disasters. Such networks might transmit privacy-sensitive information, e.g. GPS location of smartphones, which might be disclosed if the network is compromised. Privacy concerns might slow down the adoption of the technology, in particular in the scenario of social sensing where participation is voluntary, thus solutions are needed which improve privacy without compromising on the event detection accuracy. PriMaL is implemented as a machine-learning layer that works on top of an existing event detection algorithm. Experiments are run in a general simulation framework, for several network topologies and parameter values. The privacy footprint of state-of-the-art event detection algorithms is compared within the proposed framework. Results show that PriMaL is able to reduce the privacy cost of a distributed event detection algorithm below that of the corresponding centralized algorithm, within the bounds of some assumptions about the protocol. Moreover the performance of the distributed algorithm is not statistically worse than that of the centralized algorithm.