# Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis

arXiv: https://arxiv.org/abs/2608.14729 · HTML: https://mlsanity.com/paper/2608.14729/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images](https://mlsanity.com/paper/2303.14126/) (2023)
- [Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images](https://mlsanity.com/paper/2304.13023/) (2023)
- [FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models](https://mlsanity.com/paper/2404.13306/) (2024)
- [Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value](https://mlsanity.com/paper/2208.03608/) (2022)
- [Efficient Concept Induction for Description Logics](https://mlsanity.com/paper/1812.03243/) (2018)
- [On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis](https://mlsanity.com/paper/2404.13567/) (2024)
- [Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection](https://mlsanity.com/paper/2404.18649/) (2024)
- [A Case Study on Concept Induction for Neuron-Level Interpretability in CNN](https://mlsanity.com/paper/2603.00197/) (2026)

## Abstract (arXiv)

Fake/synthetic images are increasingly prevalent, but it remains unclear whether Convolutional Neural Networks (CNNs) process real and fake images in the same internal manner. This work examines the hypothesis that CNNs represent real and fake images differently, such that fake images induce different hidden-layer activation patterns even when semantic content is preserved. The hypothesis is evaluated in scene recognition settings using trained CNN models. Dense-layer activations are extracted, and neurosymbolic methods assign semantic labels to selected neurons. For each real test image, corresponding fake images are generated with similar semantic content using object-label-guided text-to-image and image-to-image generation based on Stable Diffusion variants. Paired real-fake activation patterns are then compared statistically. Additional experiments with another dataset, CNN architecture, generative model, and JPEG/blur degradation analysis assess robustness. Results suggest that fake images evoke different hidden-neuron activations, and these differences are not explained only by simple image degradation. Overall, the findings indicate that real and fake images differ in CNN hidden-layer activation behavior at least in some settings, which opens the door for follow-up work on making use of this different behavior to improve fake image detection.