AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabulary

TL;DR

AccEar demonstrates that accelerometer sensors can be exploited to reconstruct high-fidelity audio from smartphones, posing a significant privacy threat by enabling unconstrained acoustic eavesdropping using a cGAN model.

Contribution

This work introduces AccEar, a novel attack leveraging accelerometer data and cGANs to reconstruct any audio played on smartphones, surpassing previous limitations of vocabulary scope.

Findings

Successfully reconstructs speech from accelerometer data in various scenarios

Employs cGAN to enhance spectrograms for high-fidelity audio reconstruction

Effective across different device models, sampling rates, and volume levels

Abstract

With the increasing popularity of voice-based applications, acoustic eavesdropping has become a serious threat to users' privacy. While on smartphones the access to microphones needs an explicit user permission, acoustic eavesdropping attacks can rely on motion sensors (such as accelerometer and gyroscope), which access is unrestricted. However, previous instances of such attacks can only recognize a limited set of pre-trained words or phrases. In this paper, we present AccEar, an accelerometerbased acoustic eavesdropping attack that can reconstruct any audio played on the smartphone's loudspeaker with unconstrained vocabulary. We show that an attacker can employ a conditional Generative Adversarial Network (cGAN) to reconstruct highfidelity audio from low-frequency accelerometer signals. The presented cGAN model learns to recreate high-frequency components of the user's voice from low-frequency accelerometer signals through spectrogram enhancement. We assess the feasibility and effectiveness of AccEar attack in a thorough set of experiments using audio from 16 public personalities. As shown by the results in both objective and subjective evaluations, AccEar successfully reconstructs user speeches from accelerometer signals in different scenarios including varying sampling rate, audio volume, device model, etc.