# On the use of Benford's law to detect GAN-generated images

arXiv: https://arxiv.org/abs/2004.07682 · HTML: https://mlsanity.com/paper/2004.07682/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 11 of 11)

- [CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images](https://mlsanity.com/paper/2303.14126/) (2023)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection](https://mlsanity.com/paper/2210.02746/) (2022)
- [An Overview on the Generation and Detection of Synthetic and Manipulated Satellite Images](https://mlsanity.com/paper/2209.08984/) (2022)
- [Rethinking Neural Networks With Benford's Law](https://mlsanity.com/paper/2102.03313/) (2021)
- [An Investigation of "Benford's" Law Divergence and Machine Learning Techniques for "Intra-Class" Separability of Fingerprint Images](https://mlsanity.com/paper/2201.01699/) (2022)
- [Real or Virtual: A Video Conferencing Background Manipulation-Detection System](https://mlsanity.com/paper/2204.11853/) (2022)
- [Deep Metric Color Embeddings for Splicing Localization in Severely Degraded Images](https://mlsanity.com/paper/2206.10737/) (2022)
- [On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques](https://mlsanity.com/paper/2403.15497/) (2024)
- [A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics](https://mlsanity.com/paper/2609.39585/) (2026)

## Abstract (arXiv)

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.