Conditional Likelihood for Image Detection
Figure 1 : Conditional likelihood illustration. Our adaptive image detection method. When conditioned by real images from a specific domain (red dots), generated images become unlikely.
Paper context
Paper title: General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood Abstract: 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. Passages referencing this figure: Figure 1 : Conditional likelihood illustration. 2 ) and domain-specific images ( Fig. 1 ).
