Detecting CNN-Generated Facial Images in Real-World Scenarios

05/12/2020
by   Nils Hulzebosch, et al.
7

Artificial, CNN-generated images are now of such high quality that humans have trouble distinguishing them from real images. Several algorithmic detection methods have been proposed, but these appear to generalize poorly to data from unknown sources, making them infeasible for real-world scenarios. In this work, we present a framework for evaluating detection methods under real-world conditions, consisting of cross-model, cross-data, and post-processing evaluation, and we evaluate state-of-the-art detection methods using the proposed framework. Furthermore, we examine the usefulness of commonly used image pre-processing methods. Lastly, we evaluate human performance on detecting CNN-generated images, along with factors that influence this performance, by conducting an online survey. Our results suggest that CNN-based detection methods are not yet robust enough to be used in real-world scenarios.

READ FULL TEXT

page 1

page 2

page 4

page 8

page 11

page 13

page 15

research
01/07/2021

Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification

We reconsider the evaluation of OOD detection methods for image recognit...
research
11/16/2022

GLFF: Global and Local Feature Fusion for Face Forgery Detection

With the rapid development of deep generative models (such as Generative...
research
03/26/2022

Fusing Global and Local Features for Generalized AI-Synthesized Image Detection

With the development of the Generative Adversarial Networks (GANs) and D...
research
07/08/2022

Evaluating Systemic Error Detection Methods using Synthetic Images

We introduce SpotCheck, a framework for generating synthetic datasets to...
research
12/23/2019

CNN-generated images are surprisingly easy to spot... for now

In this work we ask whether it is possible to create a "universal" detec...
research
04/07/2021

[RE] CNN-generated images are surprisingly easy to spot...for now

This work evaluates the reproducibility of the paper "CNN-generated imag...
research
08/25/2021

Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery

Fiducial markers are commonly used in navigation assisted minimally inva...

Please sign up or login with your details

Forgot password? Click here to reset