Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
This addresses security issues for users of voice-controlled IoT systems, but it appears incremental as it builds on existing acoustic-based detection methods.
The paper tackles the vulnerability of voice-controlled IoT systems to spoofing attacks by proposing a defense strategy that detects the sound source of voice commands using acoustic features, with proof-of-concept experiments verifying its feasibility and effectiveness.
Over the last few years, a rapidly increasing number of Internet-of-Things (IoT) systems that adopt voice as the primary user input have emerged. These systems have been shown to be vulnerable to various types of voice spoofing attacks. Existing defense techniques can usually only protect from a specific type of attack or require an additional authentication step that involves another device. Such defense strategies are either not strong enough or lower the usability of the system. Based on the fact that legitimate voice commands should only come from humans rather than a playback device, we propose a novel defense strategy that is able to detect the sound source of a voice command based on its acoustic features. The proposed defense strategy does not require any information other than the voice command itself and can protect a system from multiple types of spoofing attacks. Our proof-of-concept experiments verify the feasibility and effectiveness of this defense strategy.