Quantifying Source Location Privacy Routing Performance via Divergence and Information Loss

Source location Privacy (SLP) is an important property for security critical applications deployed over a wireless sensor network. This property specifies that the location of the source of messages needs to be kept secret from an eavesdropping adversary that is able to move around the network. Most previous work on SLP has focused on developing protocols to enhance the SLP imparted to the network under various attacker models and other conditions. Other works have focused on analysing the level of SLP being imparted by a specific protocol. In this paper, we introduce the notion of a routing matrix which captures when messages are first received. We then introduce a novel approach where an optimal SLP routing matrix is derived. In this approach, the attacker's movement is modelled as a Markov chain where measures of conditional entropy and divergence are used to compare routing matrices and quantify if they provide high levels of SLP. We propose the notion of a properly competing paths that causes an attacker to divert when moving towards the source. This concept provides the basis for developing a perturbation model, similar to those used in privacy-preserving data mining. We formally prove that properly competing paths are both necessary and sufficient in ensuring the existence of an SLP-aware routing matrix and show their usage in developing an SLP-aware routing matrix. Further, we show how different SLP-aware routing matrices can be obtained through different instantiations of the framework. Those instantiations are obtained based on a notion of information loss achieved through the use of the perturbation model proposed