# Trinity Detector:text-assisted and attention mechanisms based spectral fusion for diffusion generation image detection

arXiv: https://arxiv.org/abs/2404.17254 · HTML: https://mlsanity.com/paper/2404.17254/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [Lighting (In)consistency of Paint by Text](https://mlsanity.com/paper/2207.13744/) (2022)
- [Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy](https://mlsanity.com/paper/2302.07801/) (2023)

## Built on by (most cited first, 4 of 4)

- [Explainable Synthetic Image Detection through Diffusion Timestep Ensembling](https://mlsanity.com/paper/2503.06201/) (2025)
- [The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods](https://mlsanity.com/paper/2410.18866/) (2024)
- [Present and Future Generalization of Synthetic Image Detectors](https://mlsanity.com/paper/2409.14128/) (2024)
- [Dual-Branch Convolutional Framework for Spatial and Frequency-Based Image Forgery Detection](https://mlsanity.com/paper/2509.05281/) (2025)

## Abstract (arXiv)

Artificial Intelligence Generated Content (AIGC) techniques, represented by text-to-image generation, have led to a malicious use of deep forgeries, raising concerns about the trustworthiness of multimedia content. Adapting traditional forgery detection methods to diffusion models proves challenging. Thus, this paper proposes a forgery detection method explicitly designed for diffusion models called Trinity Detector. Trinity Detector incorporates coarse-grained text features through a CLIP encoder, coherently integrating them with fine-grained artifacts in the pixel domain for comprehensive multimodal detection. To heighten sensitivity to diffusion-generated image features, a Multi-spectral Channel Attention Fusion Unit (MCAF) is designed, extracting spectral inconsistencies through adaptive fusion of diverse frequency bands and further integrating spatial co-occurrence of the two modalities. Extensive experimentation validates that our Trinity Detector method outperforms several state-of-the-art methods, our performance is competitive across all datasets and up to 17.6% improvement in transferability in the diffusion datasets.