Limits of Deepfake Detection: A Robust Estimation Viewpoint

05/09/2019

∙

by   Sakshi Agarwal, et al.

∙

0

∙

share

Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated. A robust statistics view of GANs is considered to bound the error probability for various GAN implementations in terms of their performance. The bounds are further simplified using a Euclidean approximation for the low error regime. Lastly, relationships between error probability and epidemic thresholds for spreading processes in networks are established.