CommanderSong: A systematic approach for practical adversarial voice recognition

Xuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long, Xiaokang Liu, Kai Chen, Shengzhi Zhang, Heqing Huang, Xiao Feng Wang, Carl A. Gunter

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

Abstract

The popularity of automatic speech recognition (ASR) systems, like Google Assistant, Cortana, brings in security concerns, as demonstrated by recent attacks. The impacts of such threats, however, are less clear, since they are either less stealthy (producing noise-like voice commands) or requiring the physical presence of an attack device (using ultrasound speakers or transducers). In this paper, we demonstrate that not only are more practical and surreptitious attacks feasible but they can even be automatically constructed. Specifically, we find that the voice commands can be stealthily embedded into songs, which, when played, can effectively control the target system through ASR without being noticed. For this purpose, we developed novel techniques that address a key technical challenge: integrating the commands into a song in a way that can be effectively recognized by ASR through the air, in the presence of background noise, while not being detected by a human listener. Our research shows that this can be done automatically against real world ASR applications1. We also demonstrate that such CommanderSongs can be spread through Internet (e.g., YouTube) and radio, potentially affecting millions of ASR users. Finally we present mitigation techniques that defend existing ASR systems against such threat.

Original languageEnglish (US)
Title of host publicationProceedings of the 27th USENIX Security Symposium
PublisherUSENIX Association
Pages49-64
Number of pages16
ISBN (Electronic)9781939133045
StatePublished - Jan 1 2018
Event27th USENIX Security Symposium - Baltimore, United States
Duration: Aug 15 2018Aug 17 2018

Publication series

NameProceedings of the 27th USENIX Security Symposium

Conference

Conference27th USENIX Security Symposium
CountryUnited States
CityBaltimore
Period8/15/188/17/18

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'CommanderSong: A systematic approach for practical adversarial voice recognition'. Together they form a unique fingerprint.

  • Cite this

    Yuan, X., Chen, Y., Zhao, Y., Long, Y., Liu, X., Chen, K., Zhang, S., Huang, H., Wang, X. F., & Gunter, C. A. (2018). CommanderSong: A systematic approach for practical adversarial voice recognition. In Proceedings of the 27th USENIX Security Symposium (pp. 49-64). (Proceedings of the 27th USENIX Security Symposium). USENIX Association.