FaceForensics++
Definition
A video dataset released by Rossler et al. (2019) containing 1000+ YouTube videos manipulated by four methods: DeepFakes, Face2Face, FaceSwap, and NeuralTextures. Provided at raw, light (c23), and heavy (c40) compression. The de facto community benchmark for face manipulation detection.
- Type
- Video dataset for face manipulation detection
- Source
- Rossler et al., 2019
- Scale
- 1000+ YouTube videos
- Manipulation methods
- DeepFakes, Face2Face, FaceSwap, NeuralTextures
- Compression tiers
- Raw, light (c23), heavy (c40)
Common questions
Why does FaceForensics++ include multiple compression levels?+
Real-world deepfake videos are usually re-encoded and shared through platforms that recompress them, degrading the subtle artifacts detectors rely on, so testing at raw, light, and heavy compression shows how well a detection method holds up under realistic distribution conditions rather than only on pristine footage.
Is strong performance on FaceForensics++ enough to certify a detector for casework?+
No, because the dataset's manipulation methods and source footage are now several years old, detectors trained or benchmarked only on it can perform poorly against newer generation techniques, so forensic use typically requires testing against current, case-relevant manipulation methods as well.
Related terms
- CLIP-Based Detection
- Detection approach using OpenAI CLIP or similar vision-language foundation models as a feature extractor. The broad pre-training enables generalisation to generation methods...
- CNN Residual Detector
- A convolutional neural network trained on the high-frequency residual image, the difference between the original and a de-noised version, to classify whether...
- Detection Generalisation
- The capacity of a trained detector to correctly identify deepfakes produced by generators not seen during training. Low generalisation is the central...
- Frequency-Domain Analysis
- Detection approach that transforms image patches into the frequency domain (DCT or FFT) to expose periodic artifacts introduced by upsampling layers in...
- Frequency-Domain Artefact
- A periodic or statistical anomaly in the Fourier spectrum of an image or audio signal introduced by the generation pipeline's upsampling, filter,...
- Generalisation Gap
- The drop in detection accuracy when a classifier trained on one generation method is applied to a different method. Caused by learning...
- Noiseprint
- A CNN-based camera-model fingerprint extractor by Cozzolino and Verdoliva. Applied to deepfakes, it reveals inconsistency between the camera fingerprint in the genuine...
- Physiological Signal
- A biological process visible in video, such as eye blinking, rPPG (remote photoplethysmography), and head micro-motion from the cardiac cycle, that deepfake...
- Remote Photoplethysmography (rPPG)
- A technique that detects the pulse-driven skin-colour variation in a face video without contact sensors. In real video, this signal is present...
- rPPG
- Remote photoplethysmography. A technique for measuring heart rate from subtle periodic colour changes in facial skin caused by blood-volume pulses. Authentic video...
- XceptionNet
- A depthwise-separable convolutional architecture proposed by Rossler et al. as the baseline binary classifier in FaceForensics++. Trained to distinguish real from manipulated...