DeepFake Detection Based on the Discrepancy Between the Face and its Context
This addresses the challenge of detecting deepfake manipulations for security and media verification, offering an incremental improvement by combining face and context recognition networks.
The paper tackles the problem of detecting face swapping and identity manipulations in single images by exploiting discrepancies between the manipulated face region and its unchanged context, achieving state-of-the-art results on benchmarks like FaceForensics++, Celeb-DF-v2, and DFDC.
We propose a method for detecting face swapping and other identity manipulations in single images. Face swapping methods, such as DeepFake, manipulate the face region, aiming to adjust the face to the appearance of its context, while leaving the context unchanged. We show that this modus operandi produces discrepancies between the two regions. These discrepancies offer exploitable telltale signs of manipulation. Our approach involves two networks: (i) a face identification network that considers the face region bounded by a tight semantic segmentation, and (ii) a context recognition network that considers the face context (e.g., hair, ears, neck). We describe a method which uses the recognition signals from our two networks to detect such discrepancies, providing a complementary detection signal that improves conventional real vs. fake classifiers commonly used for detecting fake images. Our method achieves state of the art results on the FaceForensics++, Celeb-DF-v2, and DFDC benchmarks for face manipulation detection, and even generalizes to detect fakes produced by unseen methods.