On the use of Benford's law to detect GAN-generated images
This addresses the need to regulate synthetic imagery for social and political security, but it is incremental as it applies an existing statistical law to a new detection task.
The paper tackled the problem of detecting GAN-generated images to mitigate risks like fake news by using Benford's law on DCT coefficients, resulting in a compact feature vector for simple classification.
The advent of Generative Adversarial Network (GAN) architectures has given anyone the ability of generating incredibly realistic synthetic imagery. The malicious diffusion of GAN-generated images may lead to serious social and political consequences (e.g., fake news spreading, opinion formation, etc.). It is therefore important to regulate the widespread distribution of synthetic imagery by developing solutions able to detect them. In this paper, we study the possibility of using Benford's law to discriminate GAN-generated images from natural photographs. Benford's law describes the distribution of the most significant digit for quantized Discrete Cosine Transform (DCT) coefficients. Extending and generalizing this property, we show that it is possible to extract a compact feature vector from an image. This feature vector can be fed to an extremely simple classifier for GAN-generated image detection purpose.