Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery

The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems. Recent studies suggest that diffusion pipelines unintentionally imprint persistent statistical traces, known as signal-leaks, within their outputs, particularly in latent representations. Building on this observation, we propose Proto-LeakNet, a signal-leak-aware and interpretable attribution framework that integrates closed-set classification with a density-based open-set evaluation on the learned embeddings, enabling analysis of unseen generators without retraining. Acting in the latent domain of diffusion models, our method re-simulates partial forward diffusion to expose residual generator-specific cues. A temporal attention encoder aggregates multi-step latent features, while a feature-weighted prototype head structures the embedding space and enables transparent attribution. Trained solely on closed data and achieving a Macro AUC of 98.13%, Proto-LeakNet learns a latent geometry that remains robust under post-processing, surpassing state-of-the-art methods, and achieves strong separability both between real images and known generators, and between known and unseen ones. The codebase will be available after acceptance.

Key Contributions

• Signal-leak-aware latent-domain attribution: re-simulates partial forward diffusion to extract generator-specific statistical traces from diffusion model latent representations
• Temporal attention encoder that aggregates multi-step latent features across diffusion timesteps (t∈{0,5,10}) via a ResNet-18 + attention pooling backbone
• Feature-weighted prototype head enabling interpretable closed-set attribution and density-based open-set evaluation of unseen generators without retraining

🛡️ Threat Analysis

Details

Similar Papers