# On the Separation of Human and AI-Generated Images in CLIP Embedding Space

arXiv: https://arxiv.org/abs/2608.25609 · HTML: https://mlsanity.com/paper/2608.25609/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Fourier Spectrum Discrepancies in Deep Network Generated Images](https://mlsanity.com/paper/1911.06465/) (2019)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)](https://mlsanity.com/paper/2402.10376/) (2024)
- [The ArtBench Dataset: Benchmarking Generative Models with Artworks](https://mlsanity.com/paper/2206.11404/) (2022)
- [A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Styles](https://mlsanity.com/paper/2502.15856/) (2025)
- [Detecting AI-Generated Images via CLIP](https://mlsanity.com/paper/2404.08788/) (2024)
- [Improving Interpretability and Robustness for the Detection of AI-Generated Images](https://mlsanity.com/paper/2406.15035/) (2024)
- [Artificial Intelligence and Misinformation in Art: Can Vision Language Models Judge the Hand or the Machine Behind the Canvas?](https://mlsanity.com/paper/2508.01408/) (2025)

## Abstract (arXiv)

We identify a previously unreported phenomenon in CLIP representations: human and AI-generated paintings spontaneously separate along the dominant principal directions of their joint embedding distribution, without any supervised objective designed to distinguish the two classes. Rather than exploiting this phenomenon for detection, our objective is to interpret it: we seek to identify the visual information underlying the separation and to trace it back from the embedding space to the image domain. We pursue this objective through a progressive investigation combining interpretable image representations with gradient-based inversion, used systematically as an experimental probe of the relationships identified in feature space. Robustness experiments and increasingly expressive statistical descriptors progressively rule out several intuitive explanations based on global image properties and simple local statistics, and point instead to distributed multiscale image structure. Multiscale scattering provides the most informative interpretable representation considered, but offers only a partial account of the phenomenon. Direct inversion provides a complementary and striking observation: substantial displacements along the dominant CLIP directions can be induced by image perturbations that remain nearly imperceptible to human observers, showing that the directions involved in the separation are highly sensitive to image variations with very low perceptual salience for humans. Taken together, these results reveal a significant difference between the visual evidence reflected in CLIP representations and that readily accessible to human perception, raising broader questions about the relationship between artificial and human vision and, ultimately, between artificial and human aesthetic judgment.