Detecting CNN-Generated Facial Images in Real-World Scenarios

By Nils Hulzebosch, Sarah Ibrahimi, Marcel Worring. 2020

95 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models (2020, background): “digitally created or manipulated in some way [14], [20], [21], [26].”
AI-synthesized faces are indistinguishable from real faces and more trustworthy (2022, result): “This hyperphotorealism is consistent with recent findings (10, 11).”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, background): “have recently performed in [61] an in-depth analysis of this face manipulation considering different scenarios such as cross-model, cross-data, and post-processing.”
Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection (2023, background): “In addition, some individuals, even non-experts, can malevolently manipulate or create fake images or videos for political or economic purposes, leading to serious social problems [17].”