DeepAI AI Chat
Log In Sign Up

Limits of Deepfake Detection: A Robust Estimation Viewpoint

by   Sakshi Agarwal, et al.
University of Illinois at Urbana-Champaign

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.


page 1

page 2

page 3

page 4


Minimum Probability of Error of List M-ary Hypothesis Testing

We study a variation of Bayesian M-ary hypothesis testing in which the t...

Active Hypothesis Testing: Beyond Chernoff-Stein

An active hypothesis testing problem is formulated. In this problem, the...

Hypothesis Testing with Privacy Constraints Over A Noisy Channel

We consider a hypothesis testing problem with privacy constraints over a...

A Finite Block Length Achievability Bound for Low Probability of Detection Communication

Low probability of detection (or covert) communication refers to the sce...

On the Reliability Function of Distributed Hypothesis Testing Under Optimal Detection

The distributed hypothesis-testing problem with full side-information is...

Phase Transitions in the Detection of Correlated Databases

We study the problem of detecting the correlation between two Gaussian d...

Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation

GAN-generated image detection now becomes the first line of defense agai...