Abstract
Machine learning (ML) models for deepfake detection are important for countering the threat of such videos. However, human detection is also critical because automated approaches may not always be available to people online. This study compares ML models versus humans for deepfake detection. Results surprisingly showed that humans performed better. Implications of our work are discussed.
| Original language | English |
|---|---|
| Pages (from-to) | 917-919 |
| Number of pages | 3 |
| Journal | Proceedings of the Association for Information Science and Technology |
| Volume | 61 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Oct 2024 |
| Externally published | Yes |
Bibliographical note
Publisher Copyright:87 Annual Meeting of the Association for Information Science & Technology | Oct. 25 – 29, 2024 | Calgary, AB, Canada.
ASJC Scopus Subject Areas
- General Computer Science
- Library and Information Sciences
Keywords
- Accuracy
- Deepfake detection
- Human detection
- Machine learning models
- Performance