Causal Fingerprints of AI Generative Models

arXiv:2509.15406v2 Announce Type: replace Abstract: AI generative models leave implicit traces in their generated images, which are commonly referred to as model fingerprints and are exploited for source attribution. Prior methods rely on model-specific cues or synthesis artifacts, yielding limited fingerprints that may generalize poorly across different generative models. We argue that a complete model fingerprint should reflect the causality between image provenance and model traces, a direction largely unexplored. To this end, we conceptualize the causal fingerprint of generative models, and propose a causality-decoupling framework that disentangles it from image-specific content and style in a semantic-invariant latent space derived from pre-trained diffusion reconstruction residual. We further enhance fingerprint granularity with diverse feature representations. We validate causality by assessing attribution performance across representative GANs and diffusion models and by achieving source anonymization using counterfactual examples generated from causal fingerprints. Experiments show our approach outperforms existing methods in model attribution, indicating strong potential for forgery detection, model copyright tracing, and identity protection.

Related

• HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
• How Noise Benefits AI-generated Image Detection
• PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
• Detecting Diffusion-generated Images via Dynamic Assembly ForestsDetecting Diffusion-generated Images via Dynamic Assembly Forests
• Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes

Source: arXiv cs.CV | 2026-04-15