My(o) Armband Leaks Passwords: An EMG and IMU Based Keylogging Side-Channel Attack

TL;DR

This paper demonstrates that EMG sensor data from wearables like the Myo Armband can effectively be used to perform keylogging side-channel attacks, revealing passwords with significant accuracy.

Contribution

It introduces a novel EMG-based side-channel attack for password inference using neural networks, with an extensive open dataset and code for reproducibility.

Findings

EMG data outperforms accelerometer and gyroscope for keystroke detection

Achieved 76% balanced accuracy in keystroke detection

Achieved 32% top-3 accuracy for password key identification

Abstract

Wearables that constantly collect various sensor data of their users increase the chances for inferences of unintentional and sensitive information such as passwords typed on a physical keyboard. We take a thorough look at the potential of using electromyographic (EMG) data, a sensor modality which is new to the market but has lately gained attention in the context of wearables for augmented reality (AR), for a keylogging side-channel attack. Our approach is based on neural networks for a between-subject attack in a realistic scenario using the Myo Armband to collect the sensor data. In our approach, the EMG data has proven to be the most prominent source of information compared to the accelerometer and gyroscope, increasing the keystroke detection performance. For our end-to-end approach on raw data, we report a mean balanced accuracy of about 76 % for the keystroke detection and a mean top-3 key accuracy of about 32 % on 52 classes for the key identification on passwords of varying strengths. We have created an extensive dataset including more than 310 000 keystrokes recorded from 37 volunteers, which is available as open access along with the source code used to create the given results.