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

TL;DR

PRADA is a novel, interpretable method that detects AR-generated images by analyzing probability ratios, effectively attributing images to their source models with high accuracy.

Contribution

It introduces a simple probability-ratio-based approach for reliable detection and attribution of images generated by autoregressive models, filling a key gap in AR image detection.

Findings

PRADA effectively detects images from eight class-to-image models.

PRADA accurately attributes images to their source models.

The method outperforms existing detection techniques.

Abstract

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.