# Efficient Zero-Shot AI-Generated Image Detection

arXiv: https://arxiv.org/abs/2603.21619 · HTML: https://mlsanity.com/paper/2603.21619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error](https://mlsanity.com/paper/2401.17879/) (2024)
- [C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection](https://mlsanity.com/paper/2408.09647/) (2024)
- [From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models](https://mlsanity.com/paper/2310.08825/) (2023)
- [FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion](https://mlsanity.com/paper/2406.08603/) (2024)
- [Is Artificial Intelligence Generated Image Detection a Solved Problem?](https://mlsanity.com/paper/2505.12335/) (2025)
- [FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error](https://mlsanity.com/paper/2412.07140/) (2024)
- [RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection](https://mlsanity.com/paper/2405.20112/) (2024)
- [Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors](https://mlsanity.com/paper/2411.07472/) (2024)
- [Characteristics and prevalence of fake social media profiles with AI-generated faces](https://mlsanity.com/paper/2401.02627/) (2024)
- [Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images](https://mlsanity.com/paper/2504.15470/) (2025)
- [OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection](https://mlsanity.com/paper/2509.09495/) (2025)
- [Training-free Detection of AI-generated images via Cropping Robustness](https://mlsanity.com/paper/2511.14030/) (2025)
- [HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images](https://mlsanity.com/paper/2412.20704/) (2024)
- [Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models](https://mlsanity.com/paper/2411.19117/) (2024)
- [Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes](https://mlsanity.com/paper/2505.19582/) (2025)
- [SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection](https://mlsanity.com/paper/2509.22070/) (2025)

## Abstract (arXiv)

The rapid progress of text-to-image models has made AI-generated images increasingly realistic, posing significant challenges for accurate detection of generated content. While training-based detectors often suffer from limited generalization to unseen images, training-free approaches offer better robustness, yet struggle to capture subtle discrepancies between real and synthetic images. In this work, we propose a training-free AI-generated image detection method that measures representation sensitivity to structured frequency perturbations, enabling detection of minute manipulations. The proposed method is computationally lightweight, as perturbation generation requires only a single Fourier transform for an input image. As a result, it achieves one to two orders of magnitude faster inference than most training-free detectors.Extensive experiments on challenging benchmarks demonstrate the efficacy of our method over state-of-the-art (SoTA). In particular, on OpenFake benchmark, our method improves AUC by nearly 10% compared to SoTA, while maintaining substantially lower computational cost.