ISCA Archive SPSC 2021
ISCA Archive SPSC 2021

Exploiting the Gaps Between Human and Machine Understanding of Audio: Frameworks, Attacks, and Defenses

Patrick Traynor

Modern machine learning techniques now enable a wide range of voice-driven systems. Such systems not only power our personal assistants and transcribe our text message, but also enable the creation of convincing virtual avatars, assist in air traffic control, and give voice to those who can no longer speak. However, the algorithms underlying these systems process and "understand" audio far differently that humans do, creating substantial vulnerabilities. In this talk, I discuss a range of such attacks and how they target real systems, a shared framework by which these attacks can be compared, and how such vulnerabilities might actually serve as the basis of stronger systems.


Cite as: Traynor, P. (2021) Exploiting the Gaps Between Human and Machine Understanding of Audio: Frameworks, Attacks, and Defenses. Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication,

@inproceedings{traynor21_spsc,
  author={Patrick Traynor},
  title={{Exploiting the Gaps Between Human and Machine Understanding of Audio: Frameworks, Attacks, and Defenses}},
  year=2021,
  booktitle={Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication},
  pages={}
}