The Same Name Is Not Always the Same: Correlating and Tracing Forgery Methods across Various Deepfake Datasets

The Same Name Is Not Always the Same: Correlating and Tracing Forgery Methods across Various Deepfake Datasets

Deepfakes are becoming increasingly ubiquitous, particularly in facial manipulation. Numerous researchers and companies have released multiple datasets of face deepfakes labeled to indicate different methods of forgery. However, naming these labels is often arbitrary and inconsistent, leading to the...

Full description

Bibliographic Details
Main Authors: Yi Sun, Jun Zheng, Lingjuan Lyn, Hanyu Zhao, Jiaxing Li, Yunteng Tan, Xinyu Liu, Yuanzhang Li
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Electronics
Subjects:
deepfake
datasets
correlation
traceability
clustering
Calinski Harabasz
Online Access:https://www.mdpi.com/2079-9292/12/11/2353

Similar Items

Similar Items