# Adversarial Attacks on Co-Occurrence Features for GAN Detection

arXiv: https://arxiv.org/abs/2009.07456 · HTML: https://mlsanity.com/paper/2009.07456/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints](https://mlsanity.com/paper/2512.11771/) (2025)
- [Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances](https://mlsanity.com/paper/2303.15533/) (2023)
- [Current Status and Trends in Image Anti-Forensics Research: A Bibliometric Analysis](https://mlsanity.com/paper/2408.11365/) (2024)

## Abstract (arXiv)

Improvements in Generative Adversarial Networks (GANs) have greatly reduced the difficulty of producing new, photo-realistic images with unique semantic meaning. With this rise in ability to generate fake images comes demand to detect them. While numerous methods have been developed for this task, the majority of them remain vulnerable to adversarial attacks. In this paper, develop two novel adversarial attacks on co-occurrence based GAN detectors. These are the first attacks to be presented against such a detector. We show that our method can reduce accuracy from over 98% to less than 4%, with no knowledge of the deep learning model or weights. Furthermore, accuracy can be reduced to 0% with full knowledge of the deep learning model details.