Correlating GSM and 802.11 Hardware Identifiers

Abstract—The hardware identifiers of common wireless pro-tocols can be exploited by adversaries for both tracking and physical device association. Rather than examining hardware identifiers in isolation, we observe that many modern devices are equipped with multiple wireless interfaces of different physical types, e.g. GSM and 802.11, suggesting that there exists utility in cross-protocol hardware identifier correlation. This research empir-ically examines the feasibility of such cross-protocol association, concentrating on correlating a GSM hardware identifier to that of the 802.11 hardware identifier on the same device. Our dataset includes 18 distinct mobile devices, with identifiers collected over time at disparate locations. We develop correlation techniques from the perspective of two adversaries: i) limited, able to observe identifiers only in time and space; and ii) a more advanced adversary with visibility into the data stream of each protocol. We first test correlation via temporal and spatial analysis using only basic signal collection, mimicking an RF collection with no decryption or data processing capability. Using a constrained optimization algorithm over temporal and spatial data to perform matching, we demonstrate increasing association accuracy over time, up to ≈80 % in our experiments. Our second approach simulates the added capability to collect, decrypt, and reconstruct specific application protocol data, and parses the data of one protocol using search terms derived from the other. With the combined techniques, we achieve 100 % accuracy and precision. I