FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces

TL;DR

This paper introduces FaceForensics, a large-scale dataset of half a million manipulated videos for advancing fake face detection, along with benchmarks for classification, segmentation, and forgery realism.

Contribution

It provides the largest dataset of face manipulation videos and establishes new benchmarks for forensic detection tasks.

Findings

Dataset exceeds existing datasets by an order of magnitude.

Benchmarks include classification and segmentation across various compression levels.

Evaluation of forgery indistinguishability with ground truth models.

Abstract

With recent advances in computer vision and graphics, it is now possible to generate videos with extremely realistic synthetic faces, even in real time. Countless applications are possible, some of which raise a legitimate alarm, calling for reliable detectors of fake videos. In fact, distinguishing between original and manipulated video can be a challenge for humans and computers alike, especially when the videos are compressed or have low resolution, as it often happens on social networks. Research on the detection of face manipulations has been seriously hampered by the lack of adequate datasets. To this end, we introduce a novel face manipulation dataset of about half a million edited images (from over 1000 videos). The manipulations have been generated with a state-of-the-art face editing approach. It exceeds all existing video manipulation datasets by at least an order of magnitude. Using our new dataset, we introduce benchmarks for classical image forensic tasks, including classification and segmentation, considering videos compressed at various quality levels. In addition, we introduce a benchmark evaluation for creating indistinguishable forgeries with known ground truth; for instance with generative refinement models.