PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Damm, Simon, Ricker, Jonas, Petzka, Henning, Fischer, Asja
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908950072393728
author Damm, Simon
Ricker, Jonas
Petzka, Henning
Fischer, Asja
author_facet Damm, Simon
Ricker, Jonas
Petzka, Henning
Fischer, Asja
contents Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for efficiently generating deceptively real-looking images, further increasing the need for reliable detection methods. However, to date there is a lack of work specifically targeting the detection of images generated by AR image generators. In this work, we present PRADA (Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images), a simple and interpretable approach that can reliably detect AR-generated images and attribute them to their respective source model. The key idea is to inspect the ratio of a model's conditional and unconditional probability for the autoregressive token sequence representing a given image. Whenever an image is generated by a particular model, its probability ratio shows unique characteristics which are not present for images generated by other models or real images. We exploit these characteristics for threshold-based attribution and detection by calibrating a simple, model-specific score function. Our experimental evaluation shows that PRADA is highly effective against eight class-to-image and four text-to-image models. We release our code and data at github.com/jonasricker/prada.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
Damm, Simon
Ricker, Jonas
Petzka, Henning
Fischer, Asja
Computer Vision and Pattern Recognition
Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for efficiently generating deceptively real-looking images, further increasing the need for reliable detection methods. However, to date there is a lack of work specifically targeting the detection of images generated by AR image generators. In this work, we present PRADA (Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images), a simple and interpretable approach that can reliably detect AR-generated images and attribute them to their respective source model. The key idea is to inspect the ratio of a model's conditional and unconditional probability for the autoregressive token sequence representing a given image. Whenever an image is generated by a particular model, its probability ratio shows unique characteristics which are not present for images generated by other models or real images. We exploit these characteristics for threshold-based attribution and detection by calibrating a simple, model-specific score function. Our experimental evaluation shows that PRADA is highly effective against eight class-to-image and four text-to-image models. We release our code and data at github.com/jonasricker/prada.
title PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20068