Exploiting the Final Component of Generator Architectures for AI-Generated Image Detection

2026-01-28

AI Summary

This work addresses the limited generalization of existing AI-generated image detection methods when confronted with unseen generators. To overcome this challenge, the authors propose a universal contamination strategy based on the final architectural components of generative models. By constructing a taxonomy of these components and applying simulated contamination to real images, the method enriches the training data to better mimic artifacts from diverse generators. Leveraging the DINOv3 backbone and few-shot fine-tuning, the approach trains a cross-generator detector that requires only 100 samples per generator class. Evaluated on 22 previously unseen generators, the model achieves an average detection accuracy of 98.83%, demonstrating significantly improved generalization capability against unknown generative models.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

With the rapid proliferation of powerful image generators, accurate detection of AI-generated images has become essential for maintaining a trustworthy online environment. However, existing deepfake detectors often generalize poorly to images produced by unseen generators. Notably, despite being trained under vastly different paradigms, such as diffusion or autoregressive modeling, many modern image generators share common final architectural components that serve as the last stage for converting intermediate representations into images. Motivated by this insight, we propose to"contaminate"real images using the generator's final component and train a detector to distinguish them from the original real images. We further introduce a taxonomy based on generators'final components and categorize 21 widely used generators accordingly, enabling a comprehensive investigation of our method's generalization capability. Using only 100 samples from each of three representative categories, our detector-fine-tuned on the DINOv3 backbone-achieves an average accuracy of 98.83% across 22 testing sets from unseen generators.

Problem

• AI-generated image detection
• generalization
• unseen generators
• deepfake detection
• image forensics

Innovation

• final component
• AI-generated image detection
• generalization
• image generator taxonomy
• detector fine-tuning