Publication result detail

Practical lessons of (deep)faking human speech

FIRC, A.; MALINKA, K.

Original Title

Practical lessons of (deep)faking human speech

English Title

Practical lessons of (deep)faking human speech

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

Deepfakes are an emerging threat to computer security. Various usages range from spreading fake news to identity theft. A particular subset of this problem is using deepfakes to spoof biometrics systems. The attacker spoofs an individual's identity by synthesizing his voice or appearance and uses this spoofed identity to gain access into a system secured by biometrics authentication. In our former research, we demonstrated that speech deepfakes present a threat not only to voice biometrics systems but also to people. We presented that text-dependent verification is more resilient to deepfakes than text-independent verification. This paper aims to summarize our former research with its results and to highlight the powerful role of open-source tools in this area.

English abstract

Deepfakes are an emerging threat to computer security. Various usages range from spreading fake news to identity theft. A particular subset of this problem is using deepfakes to spoof biometrics systems. The attacker spoofs an individual's identity by synthesizing his voice or appearance and uses this spoofed identity to gain access into a system secured by biometrics authentication. In our former research, we demonstrated that speech deepfakes present a threat not only to voice biometrics systems but also to people. We presented that text-dependent verification is more resilient to deepfakes than text-independent verification. This paper aims to summarize our former research with its results and to highlight the powerful role of open-source tools in this area.

Keywords

deepfakes, biometrics, spoofing attack, impersonation

Key words in English

deepfakes, biometrics, spoofing attack, impersonation

Authors

FIRC, A.; MALINKA, K.

RIV year

2023

Released

30.05.2022

Publisher

Czech Open Systems User's Group

Location

Radešín

ISBN

978-80-86583-34-1

Book

Sborník příspevků z 54. konference EurOpen.CZ, 28.5.-1.6.2022

Pages from

161

Pages to

172

Pages count

12

URL

https://europen.cz/Anot/54-1/sbornik-54.pdf

BibTex

@inproceedings{BUT177797,
  author="Anton {Firc} and Kamil {Malinka}",
  title="Practical lessons of (deep)faking human speech",
  booktitle="Sborník příspevků z 54. konference EurOpen.CZ, 28.5.-1.6.2022",
  year="2022",
  pages="161--172",
  publisher="Czech Open Systems User's Group",
  address="Radešín",
  isbn="978-80-86583-34-1",
  url="https://europen.cz/Anot/54-1/sbornik-54.pdf"
}