Maximum Privacy under Perfect Utility in Sensor Networks

Each node or sensor in a network makes a local observation that is linearly related to a set of public and private parameters. The nodes send their observations to a fusion center to allow it to estimate a set of public parameters. However, the fusion center may also abuse this information to estimate other private parameters. To prevent leakage of the private parameters, each node first sanitizes its local observation using a local privacy mechanism before transmitting it to the fusion center. We consider the maximum privacy achievable under perfect utility in terms of the Cramér-Rao lower bounds. We propose a method to maximize the estimation error for inferring the private parameters while ensuring the estimation error for inferring the public parameters remains unchanged after sanitizing the sensors' measurements.