Metamorph: Injecting Inaudible Commands into Over-the-air Voice Controlled Systems

Tao Chen, Longfei Shangguan, Zhenjiang Li, Kyle Jamieson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

52 Scopus citations

Abstract

This paper presents Metamorph, a system that generates imperceptible audio that can survive over-the-air transmission to attack the neural network of a speech recognition system. The key challenge stems from how to ensure the added perturbation of the original audio in advance at the sender side is immune to unknown signal distortions during the transmission process. Our empirical study reveals that signal distortion is mainly due to device and channel frequency selectivity but with different characteristics. This brings a chance to capture and further pre-code this impact to generate adversarial examples that are robust to the over-the-air transmission. We leverage this opportunity in Metamorph and obtain an initial perturbation that captures the core distortion's impact from only a small set of prior measurements, and then take advantage of a domain adaptation algorithm to refine the perturbation to further improve the attack distance and reliability. Moreover, we consider also reducing human perceptibility of the added perturbation. Evaluation achieves a high attack success rate (90%) over the attack distance of up to 6 m. Within a moderate distance, e.g., 3 m, Metamorph maintains this high success rate, yet can be further adapted to largely improve the audio quality, confirmed by a human perceptibility study.

Original languageEnglish (US)
Title of host publication27th Annual Network and Distributed System Security Symposium, NDSS 2020
PublisherThe Internet Society
ISBN (Electronic)1891562614, 9781891562617
DOIs
StatePublished - 2020
Event27th Annual Network and Distributed System Security Symposium, NDSS 2020 - San Diego, United States
Duration: Feb 23 2020Feb 26 2020

Publication series

Name27th Annual Network and Distributed System Security Symposium, NDSS 2020

Conference

Conference27th Annual Network and Distributed System Security Symposium, NDSS 2020
Country/TerritoryUnited States
CitySan Diego
Period2/23/202/26/20

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Metamorph: Injecting Inaudible Commands into Over-the-air Voice Controlled Systems'. Together they form a unique fingerprint.

Cite this