FakeReasoning: Towards Generalizable Forgery Detection and Reasoning

Achieving accurate and interpretable AI-generated images detection via VLMs' visual reasoning capability.

ArXiv Paper GitHub Code (coming soon) Dataset Dataset (coming soon)

Authors

Yueying Gao1, Dongliang Chang2, Bingyao Yu2, Haotian Qin1, Lei Chen2, Kongming Liang1, Zhanyu Ma1
1 PRIS, Beijing University of Posts and Telecommunications
2 Tsinghua University

Contributions

FakeReasoning: A forgery detection and reasoning framework, providing accurate detection with structured and reliable reasoning on forgery attributes.
MMFR-Dataset: A multi-modal forgery reasoning dataset, containing 100K training images and 20K evaluation images annotated with detailed reasoning on forgery attributes.

Detection and Reasoning Performance of FakeReasoning

FakeReasoning conducts forgery reasoning task in structured stages (summary, caption, reasoning and conclusion) and hierarchical steps (low-level and high-level), leading to accurate and interpretable detection.

GAN-generated image
DM-generated image
Real image I
Real image II

MMFR-Dataset

Constructed with advanced GPT-4o, MMFR-Dataset contains over 100,000 images with over 300,000 reasoning annotations as its training set.
Here we illustrate several images and according annotations from reasoning stage.

Evaluation sets include 20,000 images with over 60,000 reasoning annotations across 10 up-to-data generative models and are balanced in terms of authenticity.
Here we illustrate several real and fake images from each evaluation set.

Cite Our Work

@article{gao2025fakereasoning,
  title={FakeReasoning: Towards Generalizable Forgery Detection and Reasoning},
  author={Gao, Yueying and Chang, Dongliang and Yu, Bingyao and Qin, Haotian and Chen, Lei and Liang, Kongming and Ma, Zhanyu},
  journal={arXiv preprint arXiv:2503.21210},
  year={2025},
  url={https://arxiv.org/abs/2503.21210}
}