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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Giusti, Claudio, Guarnera, Luca, Battiato, Sebastiano
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911267670720512
author Giusti, Claudio
Guarnera, Luca
Battiato, Sebastiano
author_facet Giusti, Claudio
Guarnera, Luca
Battiato, Sebastiano
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
Giusti, Claudio
Guarnera, Luca
Battiato, Sebastiano
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.04260