MicPrint: acoustic sensor fingerprinting for spoof-resistant mobile device authentication
MicPrint: acoustic sensor fingerprinting for spoof-resistant mobile device authentication
复制标题
DOI：
10.1145/3360774.3360801
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Yongwoo Lee;Jingjie Li;Younghyun Kim
中科院分区：
文献类型：
--
作者：
Yongwoo Lee;Jingjie Li;Younghyun Kim
智能手机是最常用的计算平台，用于访问互联网上的敏感和重要信息。除了用户身份之外，对智能手机的身份进行身份验证是一种广泛采用的安全增强方法，因为传统的用户身份验证方法（例如密码输入）本身往往无法提供强有力的保护。在本文中，我们提出了一种基于传感器的设备指纹技术，用于识别和验证单个移动设备。我们的技术称为 MicPrint，利用移动设备中嵌入式麦克风由于制造差异而产生的独特特性，以便唯一地识别每个设备。与传统的基于传感器的设备指纹识别容易受到恶意软件欺骗攻击不同，MicPrint 从根本上具有防欺骗性，因为它使用的声学特征仅在用户堵塞麦克风孔时才会突出。这种简单的用户干预充当对传感器进行指纹识别的隐式许可，可以有效防止使用恶意软件进行未经授权的指纹识别。我们在 Google Pixel 1 和 Samsung Nexus 上实现了 MicPrint，以评估设备识别的准确性。我们还评估其针对简单原始数据攻击和复杂模拟攻击的安全性。结果表明，在各种环境噪声下进行多个增量训练周期后，MicPrint 可以为两种智能手机型号实现高精度和可靠性。
Smartphones are the most commonly used computing platform for accessing sensitive and important information placed on the Internet. Authenticating the smartphone's identity in addition to the user's identity is a widely adopted security augmentation method since conventional user authentication methods, such as password entry, often fail to provide strong protection by itself. In this paper, we propose a sensor-based device fingerprinting technique for identifying and authenticating individual mobile devices. Our technique, called MicPrint, exploits the unique characteristics of embedded microphones in mobile devices due to manufacturing variations in order to uniquely identify each device. Unlike conventional sensor-based device fingerprinting that are prone to spoofing attack via malware, MicPrint is fundamentally spoof-resistant since it uses acoustic features that are prominent only when the user blocks the microphone hole. This simple user intervention acts as implicit permission to fingerprint the sensor and can effectively prevent unauthorized fingerprinting using malware. We implement MicPrint on Google Pixel 1 and Samsung Nexus to evaluate the accuracy of device identification. We also evaluate its security against simple raw data attacks and sophisticated impersonation attacks. The results show that after several incremental training cycles under various environmental noises, MicPrint can achieve high accuracy and reliability for both smartphone models.