How Generalizable are Deepfake Detectors? An Empirical Study. (arXiv:2308.04177v1 [cs.CV])

Deepfake videos and images are becoming increasingly credible, posing a
significant threat given their potential to facilitate fraud or bypass access
control systems. This has motivated the development of deepfake detection
methods, in which deep learning models are trained to distinguish between real
and synthesized footage. Unfortunately, existing detection models struggle to
generalize to deepfakes from datasets they were not trained on, but little work
has been done to examine why or how this limitation can be addressed. In this …

access access control bypass control control systems deepfake deepfake detection deepfake detectors deepfake videos deep learning detection development footage fraud images study synthesized systems threat videos