arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.01042cs.SDcs.CReess.AS
收藏

AccEar:加速度计声衰减与无约束词汇

AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabulary

Shandong University(山东大学);George Mason University(乔治梅森大学)

Pengfei Hu, Hui Zhuang, Panneer Selvam Santhalingamy, Riccardo Spolaor, Parth Pathaky, Guoming Zhang, Xiuzhen Cheng

摘要:

随着基于语音的应用的日益普及,声学窃听已经成为对用户隐私的严重威胁。虽然在智能手机上访问麦克风需要明确的用户许可,但声学窃听攻击可以依赖于运动传感器(如加速度计和陀螺仪),其访问不受限制。然而,这种攻击的先前实例只能识别有限的一组预先训练的单词或短语。在本文中,我们提出了AccEar,一种基于加速度计的声学窃听攻击,可以重建智能手机扬声器上播放的任何音频,具有不受约束的词汇。我们证明了攻击者可以使用条件生成对抗网络(cGAN)从低频加速度计信号中重建高保真音频。所提出的cGAN模型通过频谱图增强从低频加速度计信号中学习重新创建用户语音的高频分量。我们评估了AccEar攻击的可行性和有效性,在一组完整的实验中使用来自16个公众人物的音频。如客观和主观评估的结果所示,AccEar在不同的场景中成功地从加速度计信号重建用户语音,包括不同的采样率、音频音量、设备模型等。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑