Detection Generalisation
Definition
The capacity of a trained detector to correctly identify deepfakes produced by generators not seen during training. Low generalisation is the central limitation of current deepfake detection systems.
- Field
- Deepfake detection
- What it measures
- Detector accuracy on generators unseen during training
- Known limitation
- Low generalisation across generator families
- Practical implication
- A detector tuned to one generator can miss deepfakes from another
Common questions
Why is poor generalisation the central weakness of deepfake detectors?+
Detectors often learn subtle artefacts specific to the generator architecture they were trained on rather than a universal signature of synthesis, so a new or updated generator can produce fakes with different artefacts that slip past a detector that scored well on its original test set.
How do labs try to compensate for weak generalisation in casework?+
Rather than relying on one detector's score, examiners typically combine multiple detection approaches, such as physiological, semantic, and signal-based methods, and corroborate any automated finding with manual frame-level and metadata review before drawing a conclusion.
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...
- FaceForensics++
- A video dataset released by Rossler et al. (2019) containing 1000+ YouTube videos manipulated by four methods: DeepFakes, Face2Face, FaceSwap, and NeuralTextures....
- 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...