PriMaL: A Privacy-Preserving Machine Learning Method for Event Detection in Distributed Sensor Networks
This addresses privacy concerns that slow adoption in social sensing applications like fire or earthquake detection, though it appears incremental as it builds on existing algorithms.
The paper tackles the problem of privacy-sensitive information disclosure in distributed sensor networks for event detection by introducing PriMaL, a privacy-preserving machine learning method that reduces privacy cost without compromising detection accuracy, achieving results where the distributed algorithm's performance is not statistically worse than the centralized one.
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.