General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Betser, Roy, Hofman, Omer, Vainshtein, Roman, Gilboa, Guy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912753005887488
author Betser, Roy
Hofman, Omer
Vainshtein, Roman
Gilboa, Guy
author_facet Betser, Roy
Hofman, Omer
Vainshtein, Roman
Gilboa, Guy
contents The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical challenge. While fully supervised, and few-shot methods have been proposed, maintaining an updated dataset is time-consuming and challenging. Consequently, zero-shot methods have gained increasing attention in recent years. We find that existing zero-shot methods often struggle to adapt to specific image domains, such as artistic images, limiting their real-world applicability. In this work, we introduce CLIDE, a novel zero-shot detection method based on conditional likelihood approximation. Our approach computes likelihoods conditioned on real images, enabling adaptation across diverse image domains. We extensively evaluate CLIDE, demonstrating SOTA performance on a large-scale general dataset and significantly outperform existing methods in domain-specific cases. These results demonstrate the robustness of our method and underscore the need of broad, domain-aware generalization for the AI-generated image detection task. Code is available at https://tinyurl.com/clide-detector.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05590
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
Betser, Roy
Hofman, Omer
Vainshtein, Roman
Gilboa, Guy
Image and Video Processing
The rapid advancement of generative models, particularly diffusion-based methods, has significantly improved the realism of synthetic images. As new generative models continuously emerge, detecting generated images remains a critical challenge. While fully supervised, and few-shot methods have been proposed, maintaining an updated dataset is time-consuming and challenging. Consequently, zero-shot methods have gained increasing attention in recent years. We find that existing zero-shot methods often struggle to adapt to specific image domains, such as artistic images, limiting their real-world applicability. In this work, we introduce CLIDE, a novel zero-shot detection method based on conditional likelihood approximation. Our approach computes likelihoods conditioned on real images, enabling adaptation across diverse image domains. We extensively evaluate CLIDE, demonstrating SOTA performance on a large-scale general dataset and significantly outperform existing methods in domain-specific cases. These results demonstrate the robustness of our method and underscore the need of broad, domain-aware generalization for the AI-generated image detection task. Code is available at https://tinyurl.com/clide-detector.
title General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood
topic Image and Video Processing
url https://arxiv.org/abs/2512.05590