Ensuring Semantic Validity in Privacy-Preserving Aggregate Statistics

Abstract

Aggregate statistics are becoming increasingly commonplace for mobile sensing applications which crowdsources data from individual users. In order to relieve user's concerns for privacy leakage, privacy preserving mechanisms have to be applied to enable the aggregator to compute aggregate statistics without learning each individual data. Although the aggregator will not know the value of the data, it is necessary to ensure the (semantic) validity of the data contributed by users. In this work, we design a privacy-preserving protocol for an aggregator to compute corrected aggregated statistics over users' data that can both preserve user's privacy and verify the semantic validity of the data. We evaluated our protocol on real-world dataset and demonstrated the efficiency of our protocol.