Coresets for differentially private k-means clustering and applications to privacy in mobile sensor networks

Abstract

Mobile sensor networks are a great source of data. By collecting data with mobile sensor nodes from individuals in a user community, e.g. using their smartphones, we can learn global information such as traffic congestion patterns in the city, location of key community facilities, and locations of gathering places. Can we publish and run queries on mobile sensor network databases without disclosing information about individual nodes?Differential privacy is a strong notion of privacy which guarantees that very little will be learned about individual records in the database, no matter what the attackers already know or wish to learn. Still, there is no practical system applying differential privacy algorithms for clustering points on real databases. This paper describes the construction of small coresets for computing k-means clustering of a set of points while preserving differential privacy. As a result, we give the first k-means clustering algorithm that is both differentially private, and has an approximation error that depends sub-linearly on the data's dimension d. Previous results introduced errors that are exponential in d.We implemented this algorithm and used it to create differentially private location data from GPS tracks. Specifically our algorithm allows clustering GPS databases generated from mobile nodes, while letting the user control the introduced noise due to privacy. We provide experimental results for the system and algorithms, and compare them to existing techniques. To the best of our knowledge, this is the first practical system that enables differentially private clustering on real data.

ObscureNet

“…These solutions are usually tailored to specific use cases and are incapable of preventing the leak of private information while maintaining the utility of data. The latter category includes federated learning frameworks [28], differential privacy algorithms [7,31], cryptographic solutions based on homomorphic encryption and compressive sensing [1,34], and privacy-preserving techniques that transform data to a subspace where private attributes can be easily identified and altered [8,11,24]. Federated learning addresses the problem of training a model given data from many users without transferring them to a server.…”

Compressive learning with privacy guarantees

“…Releasing a private synopsis of the data (similarly to our sketch) rather than directly a noisy solution has already been studied as well. EUGkM [43,48] suggests for instance to use noisy histograms for clustering (but this method is by nature limited to small dimensions), and private coresets have been investigated by Feldman et al [24,25]. For PCA, noise can be added directly on the covariance matrix [22].…”

A Comprehensive Survey on Local Differential Privacy toward Data Statistics and Analysis

“…The problem of clustering was studied under centralized DP [ 127 , 128 , 129 ]. With LDP model, Nissim and Stemmer [ 130 ] conducted 1-clustering by finding a minimum enclosing ball.…”