Detecting Signal Injection Attack-Based Morphological Alterations of ECG Measurements

Abstract

In this paper, we present an approach to detecting signal injection-based morphological alterations of ECG measurements in Body Sensor Networks (BSN). Signal injection attacks target, the usually unprotected, analog sensing interface of the sensors in a BSN and induce arbitrary signals in them. Signal injection is very dangerous because can be stealthily mounted on unsuspecting BSN users from close proximity (for example in a public place). Inducing morphological alterations in ECG measurements can have profound consequences for the user, as an adversary can easily make a person who is experiencing cardiac arrhythmia appear to be normal and thus cause immediate or long-term harm to their health. To detect signal injection-based morphological alterations, we leverage the idea that multiple physiological signals based on the same underlying physiological process (e.g., cardiac process) are inherently related to each other, i.e., have common features. Any adversarial alteration of one of the signals will not be reflected in the other signal(s) in the group. Therefore, to detect the morphological alterations in ECG measurements, we use arterial blood pressure (ABP) measurements. Both ECG and ABP measurements are alternative representation of the cardiac process. Our approach demonstrates promising results with over 90% accuracy in detecting even subtle ECG morphological alterations for both healthy subjects and those with cardiac conditions.