SafeGait: Safeguarding Gait-based Key Generation against Vision-based Side Channel Attack Using Generative Adversarial Network

Abstract

Recent works have shown that wearable or implanted devices attached at different locations of the body can generate an identical security key from their independent measurements of the same gait. This has created an opportunity to realize highly secured data exchange to and from critical implanted devices. In this paper, we first demonstrate that vision can be used to easily attack such gait-based key generations; an attacker with a commodity camera can measure the gait from a distance and generate a security key with any target wearable or implanted device faster than other legitimate devices worn at different locations of the subject’s body. To counter the attack, we propose a firewall to stop video-based gait measurements to proceed with key generation, but letting measurements from inertial measurement units (IMUs) that are widely used in wearable devices to measure the gait accelerations from the body to proceed. We implement the firewall concept with an IMU-vs-Video binary classifier that combines InceptionTime, an ensemble of deep Convolutional Neural Network (CNN) models for effective feature extraction from gait measurements, to a Generative Adversarial Network (GAN) that can generalize the classifier across subjects. Comprehensive evaluation with a real-world dataset shows that our proposed classifier can perform with an accuracy of 97.82%. Given that an attacker has to fool the classifier for multiple consecutive gait cycles to generate the complete key, the high single-cycle classification accuracy results in an extremely low probability for a video attacker to successfully pair with a target wearable device. More precisely, a video attacker would have one in a billion chance to successfully generate a 128-bit key, which would require the attacker to observe the subject for thousands of years.