Posit: an adaptive framework for lightweight IP geolocation

Abstract

Location-specific Internet services are predicated on the ability to identify the geographic position of IP hosts accurately. Fundamental to prior geolocation techniques is their reliance on landmarks with known coordinates whose distance from target hosts is intrinsically tied to the ability to make accurate location estimates. In this paper, we introduce a new lightweight framework for IP geolocation that we call Posit. The Posit framework geolocates by automatically adapting to the geographic distribution of the measurement infrastructure relative to each target host. This lightweight framework requires only a small number of Ping measurements conducted to end host targets in conjunction with a computationally efficient geographic embedding methodology. We demonstrate that Posit performs significantly better than all existing geolocation tools across a wide spectrum of measurement infrastructures with varying geographic densities. Posit is shown to geolocate hosts with median error improvements of over 50% with respect to all current measurement-based IP geolocation methodologies.