Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progress in artificial intelligence due to their potential for misuse. However, studies investigating human detection capabilities are limited. We presented genuine and deepfake audio to n = 529 individuals and asked them to identify the deepfakes. We ran our experiments in English and Mandarin to understand if language affects detection performance and decision-making rationale. We found that detection capability is unreliable. Listeners only correctly spotted the deepfakes 73% of the time, and there was no difference in detectability between the two languages. Increasing listener awareness by providing examples of speech deepfakes only improves results slightly. As speech synthesis algorithms improve and become more realistic, we can expect the detection task to become harder. The difficulty of detecting speech deepfakes confirms their potential for misuse and signals that defenses against this threat are needed.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10395974 | PMC |
| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0285333 | PLOS |
Publication Analysis
Top Keywords
Similar Publications
Moderating Synthetic Content: the Challenge of Generative AI.
Philos Technol
November 2024
University of Sussex School of Law, Politics and Sociology, Brighton, UK.
Artificially generated content threatens to seriously disrupt the public sphere. Generative AI massively facilitates the production of convincing portrayals of fabricated events. We have already begun to witness the spread of synthetic misinformation, political propaganda, and non-consensual intimate deepfakes.
View Article and Find Full Text PDFHuman detection of political speech deepfakes across transcripts, audio, and video.
Nat Commun
September 2024
Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA.
Article Synopsis
- Recent advancements in technology have made it increasingly difficult for people to distinguish between real political speeches and deepfake videos due to hyper-realistic audio and visual effects.
- A study involving 2,215 participants found that factors like misinformation rates and question framing did not significantly impact people’s ability to identify authenticity.
- The research revealed that deepfake videos with advanced text-to-speech audio were harder to detect than those with voice actors, and overall, people relied more on audio and visual cues rather than the content of the speech to discern real from fake.
Investigation of Deepfake Voice Detection Using Speech Pause Patterns: Algorithm Development and Validation.
JMIR Biomed Eng
March 2024
Klick Labs, Toronto, ON, Canada.
Background: The digital era has witnessed an escalating dependence on digital platforms for news and information, coupled with the advent of "deepfake" technology. Deepfakes, leveraging deep learning models on extensive data sets of voice recordings and images, pose substantial threats to media authenticity, potentially leading to unethical misuse such as impersonation and the dissemination of false information.
Objective: To counteract this challenge, this study aims to introduce the concept of innate biological processes to discern between authentic human voices and cloned voices.
Cortical-striatal brain network distinguishes deepfake from real speaker identity.
Commun Biol
June 2024
Cognitive and Affective Neuroscience Unit, Department of Psychology, University of Zurich, Zurich, Switzerland.
Deepfakes are viral ingredients of digital environments, and they can trick human cognition into misperceiving the fake as real. Here, we test the neurocognitive sensitivity of 25 participants to accept or reject person identities as recreated in audio deepfakes. We generate high-quality voice identity clones from natural speakers by using advanced deepfake technologies.
View Article and Find Full Text PDFWarning: Humans cannot reliably detect speech deepfakes.
PLoS One
August 2023
Department of Computer Science, University College London, London, United Kingdom.
Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progress in artificial intelligence due to their potential for misuse. However, studies investigating human detection capabilities are limited.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!