# CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier

arXiv: https://arxiv.org/abs/2505.10664 · HTML: https://mlsanity.com/paper/2505.10664/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 15 May 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection](https://mlsanity.com/paper/2104.09770/) (2021)
- [CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images](https://mlsanity.com/paper/2303.14126/) (2023)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)
- [CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection](https://mlsanity.com/paper/2402.12927/) (2024)
- [Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024](https://mlsanity.com/paper/2503.02857/) (2025)
- [WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection](https://mlsanity.com/paper/2402.11843/) (2024)
- [Detecting AI-Generated Images via CLIP](https://mlsanity.com/paper/2404.08788/) (2024)
- [Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks](https://mlsanity.com/paper/2204.04596/) (2022)

## Abstract (arXiv)

Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image classification is underexplored due to the absence of such labels during the pre-training process. This work investigates whether CLIP embeddings inherently contain information indicative of AI generation. A proposed pipeline extracts visual embeddings using a frozen CLIP model, feeds its embeddings to lightweight networks, and fine-tunes only the final classifier. Experiments on the public CIFAKE benchmark show the performance reaches 95% accuracy without language reasoning. Few-shot adaptation to curated custom with 20% of the data results in performance to 85%. A closed-source baseline (Gemini-2.0) has the best zero-shot accuracy yet fails on specific styles. Notably, some specific image types, such as wide-angle photographs and oil paintings, pose significant challenges to classification. These results indicate previously unexplored difficulties in classifying certain types of AI-generated images, revealing new and more specific questions in this domain that are worth further investigation.