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

[2608.14729] Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.14729 (cs) [Submitted on 12 Aug 2026] Title: Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis Authors: Moumita Sen Sarma , Pascal Hitzler , Eugene Y. Vasserman View a PDF of the paper titled Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis, by Moumita Sen Sarma and 2 other authors View PDF HTML (experimental) Abstract: 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. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.14729 [cs.CV] (or arXiv:2608.14729v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.14729 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Moumita Sen Sarma [ view email ] [v1] Wed, 12 Aug 2026 22:48:29 UTC (10,072 KB) Full-text links: Access Paper: View a PDF of the paper titled Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis, by Moumita Sen Sarma and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• An Real-Time Deep Fakes and Face Forgery Using Transfer Learning Algorithm#119628
• A Unified Framework for the Mechanics of Information in Convolutional Neural Network Image Space#818974
• A Unified Framework for the Mechanics of Information in Convolutional Neural Network Image Space#808982
• Extracting CNNs in the Unknown-Architecture and Feedback-Agnostic Setting#1063638
• Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection#984577