ENF Based Forensics

The electric network frequency (ENF) is a signature of power distribution networks . This can be captured by multimedia signals recorded near electrical activities. These ENF signals have multiple forensic applications. Examples of such applications include validating the time-of-recording of an ENF-containing media signal or estimating its recording location. In this paper, we examine an ENF-based application that infers the power grid in which the ENF-containing multimedia signal was recorded. We investigate various features based on the statistical differences in ENF signal obtained from different power grids to serve as signatures for the region-of-recording of the media signal. We use these features and implement a machine learning algorithm that is able to identify the power grid of the ENF extracted with high accuracy.