# Detecting Images Generated by Diffusers

arXiv: https://arxiv.org/abs/2303.05275 · HTML: https://mlsanity.com/paper/2303.05275/

## Key facts

- Cited by 12 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 30 of its 50 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## 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, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [MirrorGAN: Learning Text-to-image Generation by Redescription](https://mlsanity.com/paper/1903.05854/) (2019)
- [Exploring Temporal Coherence for More General Video Face Forgery Detection](https://mlsanity.com/paper/2108.06693/) (2021)
- [ID-Reveal: Identity-aware DeepFake Video Detection](https://mlsanity.com/paper/2012.02512/) (2020)
- [Combining EfficientNet and Vision Transformers for Video Deepfake Detection](https://mlsanity.com/paper/2107.02612/) (2021)
- [DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer](https://mlsanity.com/paper/2108.07379/) (2021)
- [MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection](https://mlsanity.com/paper/2211.10996/) (2022)
- [MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias](https://mlsanity.com/paper/2012.05225/) (2020)
- [Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection](https://mlsanity.com/paper/2206.13829/) (2022)
- [Cross-Domain Face Synthesis using a Controllable GAN](https://mlsanity.com/paper/1910.14247/) (2019)
- [The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild](https://mlsanity.com/paper/2204.12816/) (2022)

## Built on by (most cited first, 12 of 12)

- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [On the Design Fundamentals of Diffusion Models: A Survey](https://mlsanity.com/paper/2306.04542/) (2023)
- [Online Detection of AI-Generated Images](https://mlsanity.com/paper/2310.15150/) (2023)
- [Bi-LORA: A Vision-Language Approach for Synthetic Image Detection](https://mlsanity.com/paper/2404.01959/) (2024)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [Harnessing the Power of Large Vision Language Models for Synthetic Image Detection](https://mlsanity.com/paper/2404.02726/) (2024)
- [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)
- [FIDAVL: Fake Image Detection and Attribution using Vision-Language Model](https://mlsanity.com/paper/2409.03109/) (2024)
- [On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations](https://mlsanity.com/paper/2507.22398/) (2025)
- [Log-normal Mutations and their Use in Detecting Surreptitious Fake Images](https://mlsanity.com/paper/2409.15119/) (2024)
- [Exploring Strengths and Weaknesses of Super-Resolution Attack in Deepfake Detection](https://mlsanity.com/paper/2410.04205/) (2024)

## Abstract (arXiv)

This paper explores the task of detecting images generated by text-to-image diffusion models. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable Diffusion and GLIDE. Our experiments show that it is possible to detect the generated images using simple Multi-Layer Perceptrons (MLPs), starting from features extracted by CLIP, or traditional Convolutional Neural Networks (CNNs). We also observe that models trained on images generated by Stable Diffusion can detect images generated by GLIDE relatively well, however, the reverse is not true. Lastly, we find that incorporating the associated textual information with the images rarely leads to significant improvement in detection results but that the type of subject depicted in the image can have a significant impact on performance. This work provides insights into the feasibility of detecting generated images, and has implications for security and privacy concerns in real-world applications. The code to reproduce our results is available at: https://github.com/davide-coccomini/Detecting-Images-Generated-by-Diffusers