Guess the Unified Model: How Much Can We Recover from Generated Images?
With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in LLM-generated text, diffusion model images, and datasets, but the separability of unified model-generated images remains an underexplored area. We address this gap by examining separability across corruption, domains, and prompt languages using images generated by seven unified models. We show that model attribution is highly feasible as our model achieves near-perfect accuracy with around 20K images per model. Corruptions and structural perturbations have only a modest effect on attribution performance, and cross-domain generalization reveals that semantic content contributes to separability but is not the dominant signal. Finally, we observe that for most models, prompt language attribution is around chance levels, suggesting minimal language-specific visual signatures. These findings highlight consistent model-specific visual characteristics in unified models outputs and open new directions for tracing and auditing generative image pipelines.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Unsupervised High-Fidelity Facial Texture Generation and Reconstruction
Many methods have been proposed over the years to tackle the task of facial 3D geometry and texture recovery from a single image. Such methods often fail to provide high-fidelity texture without relying on 3D facial scan…
3D geometryImage GenerationTexture SynthesisTransfer Learning+1Photographic Visualization of Weather Forecasts with Generative Adversarial Networks
Outdoor webcam images are an information-dense yet accessible visualization of past and present weather conditions, and are consulted by meteorologists and the general public alike. Weather forecasts, however, are still …
The Impact of Answers in Referential Visual Dialog
In the visual dialog task GuessWhat?! two players maintain a dialog in order to identify a secret object in an image. Computationally, this is modeled using a question generation module and a guesser module for the quest…
Question GenerationQuestion-GenerationVisual DialogGoal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this en…
Deep Reinforcement LearningInformativenessQuestion GenerationQuestion-Generation+2Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
Single image generative models perform synthesis and manipulation tasks by capturing the distribution of patches within a single image. The classical (pre Deep Learning) prevailing approaches for these tasks are based on…
Image GenerationImage Manipulation