BL(u)E CRAB: A User-Centric Framework for Identifying Suspicious Bluetooth Trackers

Abstract

Given the pervasiveness of Bluetooth Low Energy (BLE)-based devices, detecting unwanted or suspicious trackers is challenging, especially due to their heterogeneity, cross-platform compatibility issues, and inconsistent detection methods. BL(u)E CRAB identifies suspicious BLE trackers based on various risk factors within minutes. It does so by collecting information including the number of encounters, time with the user, distance traveled with the user, number of areas each device appeared in, and device proximity to user. After collecting this information, BL(u)E CRAB performs an outlier detection analysis to flag suspicious devices. BL(u)E CRAB presents this information in a simple, intuitive, and customizable way for the user to determine which devices pose the biggest threat to them based on their context.