# Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection

arXiv: https://arxiv.org/abs/2402.19091 · HTML: https://mlsanity.com/paper/2402.19091/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 60 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [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)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)

## Built on by (most cited first, 30 of 89)

- [Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective](https://mlsanity.com/paper/2408.06741/) (2024)
- [A Bias-Free Training Paradigm for More General AI-generated Image Detection](https://mlsanity.com/paper/2412.17671/) (2024)
- [Any-Resolution AI-Generated Image Detection by Spectral Learning](https://mlsanity.com/paper/2411.19417/) (2024)
- [FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models](https://mlsanity.com/paper/2404.13306/) (2024)
- [AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models](https://mlsanity.com/paper/2507.02664/) (2025)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [TGIF: Text-Guided Inpainting Forgery Dataset](https://mlsanity.com/paper/2407.11566/) (2024)
- [DeCLIP: Decoding CLIP representations for deepfake localization](https://mlsanity.com/paper/2409.08849/) (2024)
- [Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection](https://mlsanity.com/paper/2506.00874/) (2025)
- [ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection](https://mlsanity.com/paper/2408.13697/) (2024)
- [SIDBench: A Python Framework for Reliably Assessing Synthetic Image Detection Methods](https://mlsanity.com/paper/2404.18552/) (2024)
- [Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review](https://mlsanity.com/paper/2502.15176/) (2025)
- [AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection](https://mlsanity.com/paper/2504.20865/) (2025)
- [Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?](https://mlsanity.com/paper/2507.10236/) (2025)
- [TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping](https://mlsanity.com/paper/2407.15500/) (2024)
- [Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning](https://mlsanity.com/paper/2508.01603/) (2025)
- [Evolution of Detection Performance throughout the Online Lifespan of Synthetic Images](https://mlsanity.com/paper/2408.11541/) (2024)
- [Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale](https://mlsanity.com/paper/2604.04634/) (2026)
- [Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models](https://mlsanity.com/paper/2602.01738/) (2026)
- [AI-Generated Image Detection: An Empirical Study and Future Research Directions](https://mlsanity.com/paper/2511.02791/) (2025)
- [DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection](https://mlsanity.com/paper/2511.13108/) (2025)
- [Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.24906/) (2026)
- [Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges](https://mlsanity.com/paper/2502.19716/) (2025)
- [RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors](https://mlsanity.com/paper/2506.03988/) (2025)
- [Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2603.10598/) (2026)
- [FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection](https://mlsanity.com/paper/2605.30062/) (2026)
- [Present and Future Generalization of Synthetic Image Detectors](https://mlsanity.com/paper/2409.14128/) (2024)
- [Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection](https://mlsanity.com/paper/2601.19430/) (2026)
- [AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection](https://mlsanity.com/paper/2603.23115/) (2026)

## Abstract (arXiv)

The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information. State-of-the-art Synthetic Image Detection (SID) research has led to strong evidence on the advantages of feature extraction from foundation models. However, such extracted features mostly encapsulate high-level visual semantics instead of fine-grained details, which are more important for the SID task. On the contrary, shallow layers encode low-level visual information. In this work, we leverage the image representations extracted by intermediate Transformer blocks of CLIP's image-encoder via a lightweight network that maps them to a learnable forgery-aware vector space capable of generalizing exceptionally well. We also employ a trainable module to incorporate the importance of each Transformer block to the final prediction. Our method is compared against the state-of-the-art by evaluating it on 20 test datasets and exhibits an average +10.6% absolute performance improvement. Notably, the best performing models require just a single epoch for training (~8 minutes). Code available at https://github.com/mever-team/rine.