CNN Residual Detector
Definition
A convolutional neural network trained on the high-frequency residual image, the difference between the original and a de-noised version, to classify whether an image was produced by a camera or a generative model.
- Input
- High-frequency residual image (original minus denoised)
- Architecture
- Convolutional neural network
- Target
- Camera-native vs generative-model origin
- Domain
- Deepfake and synthetic media detection
Common questions
Why use the residual instead of the raw image?+
Camera sensor noise and GAN or diffusion upsampling artefacts both live mainly in the high-frequency band. Working on the residual strips away scene content and lighting, which would otherwise dominate the network's attention and make it learn the wrong cues.
What limits a CNN residual detector in practice?+
Accuracy drops sharply on generator architectures not seen in training, and on images that have been recompressed, resized, or re-uploaded through social media, since those steps alter the residual statistics the network learned to key on.
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...
- Detection Generalisation
- The capacity of a trained detector to correctly identify deepfakes produced by generators not seen during training. Low generalisation is the central...
- 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...