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

2025-11-25

AI Summary

Autoregressive image generators (e.g., PixelCNN, DALL·E 1) lack effective, interpretable methods for detecting synthetic images and attributing them to specific models. Method: This paper proposes an explainable detection framework based on conditional versus unconditional token-sequence probability ratios—leveraging the inherent autoregressive, token-by-token generation property to design lightweight, model-specific scoring functions without additional training or fine-tuning. Detection and source attribution are jointly performed via probability-ratio thresholding and model calibration. Contribution/Results: Evaluated across eight class-to-image and four text-to-image autoregressive models, the method achieves significantly higher detection accuracy than state-of-the-art approaches, demonstrating strong generalization across architectures and clear interpretability through probabilistic rationales.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Detecting images generated by autoregressive models using probability ratios
• Attributing synthetic images to their specific source generation models
• Developing interpretable detection methods for autoregressive-generated images

Innovation

• Probability-ratio-based detection of autoregressive images
• Model-specific score function for attribution
• Threshold-based approach using token sequence characteristics