SUAD: Solid-Channel Ultrasound Injection Attack and Defense to Voice Assistants
Chao Liu, Zhezheng Zhu, Hao Chen, Kaiwen Guo, Penghao Wang, Xiang-Yang Li

TL;DR
This paper introduces SUAD, a novel long-range, cross-barrier inaudible attack on voice assistants via solid channels, and a universal ultrasonic perturbation defense that effectively blocks such attacks without affecting normal speech.
Contribution
It presents the first solid-channel inaudible attack method and a universal ultrasonic defense mechanism for voice assistants, enhancing security against long-range and cross-barrier threats.
Findings
SUAD Attack achieves over 89.8% success rate in activating voice assistants.
SUAD Defense blocks inaudible voice attacks with over 98% success rate.
The methods are effective across six different smartphones.
Abstract
As a versatile AI application, voice assistants (VAs) have become increasingly popular, but are vulnerable to security threats. Attackers have proposed various inaudible attacks, but are limited by cost, distance, or LoS. Therefore, we propose \name~Attack, a long-range, cross-barrier, and interference-free inaudible voice attack via solid channels. We begin by thoroughly analyzing the dispersion effect in solid channels, revealing its unique impact on signal propagation. To avoid distortions in voice commands, we design a modular command generation model that parameterizes attack distance, victim audio, and medium dispersion features to adapt to variations in the solid-channel state. Additionally, we propose SUAD Defense, a universal defense that uses ultrasonic perturbation signals to block inaudible voice attacks (IVAs) without impacting normal speech. Since the attack can occur at…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Speech Recognition and Synthesis · AI in Service Interactions
