# Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

arXiv: https://arxiv.org/abs/2407.20337 · HTML: https://mlsanity.com/paper/2407.20337/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 59 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Builds on (most cited first, 30 of 48)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)

## Built on by (most cited first, 27 of 27)

- [A Bias-Free Training Paradigm for More General AI-generated Image Detection](https://mlsanity.com/paper/2412.17671/) (2024)
- [FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error](https://mlsanity.com/paper/2412.07140/) (2024)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection](https://mlsanity.com/paper/2501.15253/) (2025)
- [AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection](https://mlsanity.com/paper/2504.20865/) (2025)
- [NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2508.01248/) (2025)
- [Rethinking Cross-Generator Image Forgery Detection through DINOv3](https://mlsanity.com/paper/2511.22471/) (2025)
- [Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models](https://mlsanity.com/paper/2602.01738/) (2026)
- [Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples](https://mlsanity.com/paper/2509.25682/) (2025)
- [Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.24906/) (2026)
- [RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors](https://mlsanity.com/paper/2506.03988/) (2025)
- [Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training](https://mlsanity.com/paper/2412.08221/) (2024)
- [Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection](https://mlsanity.com/paper/2601.19430/) (2026)
- [Generalized Design Choices for Deepfake Detectors](https://mlsanity.com/paper/2511.21507/) (2025)
- [Quality-Aware Calibration for AI-Generated Image Detection in the Wild](https://mlsanity.com/paper/2604.15027/) (2026)
- [GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection](https://mlsanity.com/paper/2509.10250/) (2025)
- [PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors](https://mlsanity.com/paper/2509.15551/) (2025)
- [Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models](https://mlsanity.com/paper/2510.03840/) (2025)
- [Fake3DGS: A Benchmark for 3D Manipulation Detection in Neural Rendering](https://mlsanity.com/paper/2604.27590/) (2026)
- [Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection](https://mlsanity.com/paper/2606.10309/) (2026)
- [Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks](https://mlsanity.com/paper/2505.03435/) (2025)
- [Prefill-Guided Thinking for zero-shot detection of AI-generated images](https://mlsanity.com/paper/2506.11031/) (2025)
- [Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection](https://mlsanity.com/paper/2510.05633/) (2025)
- [How Noise Benefits AI-generated Image Detection](https://mlsanity.com/paper/2511.16136/) (2025)
- [Multi-Feature Fusion Approach for Generative AI Images Detection](https://mlsanity.com/paper/2603.29788/) (2026)
- [FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection](https://mlsanity.com/paper/2608.03096/) (2026)
- [Prior-Conditioned Gaussian Discriminants for Generalizable AI-generated Image Detection](https://mlsanity.com/paper/2608.18523/) (2026)

## Abstract (arXiv)

Discerning between authentic content and that generated by advanced AI methods has become increasingly challenging. While previous research primarily addresses the detection of fake faces, the identification of generated natural images has only recently surfaced. This prompted the recent exploration of solutions that employ foundation vision-and-language models, like CLIP. However, the CLIP embedding space is optimized for global image-to-text alignment and is not inherently designed for deepfake detection, neglecting the potential benefits of tailored training and local image features. In this study, we propose CoDE (Contrastive Deepfake Embeddings), a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities. To sustain the training of our model, we generate a comprehensive dataset that focuses on images generated by diffusion models and encompasses a collection of 9.2 million images produced by using four different generators. Experimental results demonstrate that CoDE achieves state-of-the-art accuracy on the newly collected dataset, while also showing excellent generalization capabilities to unseen image generators. Our source code, trained models, and collected dataset are publicly available at: https://github.com/aimagelab/CoDE.